© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1912
    Prev
    Next
    INDEX
    Explanations

    instances of expectation and evidence in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arises
    -0.79
     unfolds
    -0.66
     manifests
    -0.66
    odor
    -0.66
     disappears
    -0.66
     arisen
    -0.64
    forms
    -0.63
     lasts
    -0.63
     persists
    -0.62
     vanished
    -0.61
    POSITIVE LOGITS
     hear
    1.18
     see
    1.15
     know
    0.95
     wanna
    0.91
     expect
    0.88
     find
    0.87
     understand
    0.87
     want
    0.85
     saw
    0.84
     SEE
    0.84
    Activations Density 1.165%

    No Known Activations