Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of denial or refutation statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    incinn
    -0.79
    tnc
    -0.76
    tn
    -0.76
    tags
    -0.72
    inki
    -0.71
    gone
    -0.70
    aptic
    -0.69
    rouse
    -0.68
    emetery
    -0.68
    igsaw
    -0.66
    POSITIVE LOGITS
     wrongdoing
    1.12
     accusations
    0.95
     allegations
    0.91
     involvement
    0.86
     outright
    0.83
     denying
    0.81
     charges
    0.79
     innocence
    0.77
     responsibility
    0.77
     paternity
    0.76
    Act Density 0.018%

    No Known Activations