© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    instances of unexpected revelations or twists in narratives

    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
     dstg
    -0.64
    ROM
    -0.63
    }}}
    -0.61
     PRESS
    -0.60
    AGES
    -0.59
    Reviewer
    -0.59
    STEP
    -0.58
    izabeth
    -0.58
    \":
    -0.58
     dx
    -0.55
    POSITIVE LOGITS
    encies
    0.72
    ured
    0.60
    ipment
    0.60
    ided
    0.59
     be
    0.58
    osal
    0.58
    abouts
    0.58
    uel
    0.57
    llor
    0.57
    wered
    0.57
    Activations Density 2.022%

    No Known Activations