© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2557
    Prev
    Next
    INDEX
    Explanations

    assertions of uncertainty or doubt

    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
    knit
    -0.80
    EVA
    -0.72
    keley
    -0.71
    tnc
    -0.66
    ulic
    -0.65
     Survive
    -0.65
     fortunate
    -0.65
    imov
    -0.65
    ortality
    -0.64
     hers
    -0.63
    POSITIVE LOGITS
     reservations
    0.93
     delusions
    0.84
     idea
    0.80
     intentions
    0.79
     Idea
    0.78
     suspicion
    0.78
     doubts
    0.77
     complaints
    0.76
     intention
    0.74
     theories
    0.74
    Activations Density 0.037%

    No Known Activations