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

    Neuronpedia

    INDEX
    Explanations

    verbs that imply taking some form of action

    oai_token-act-pair · gpt-3.5-turbo

    instances of denial or avoidance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.64
    soDeliveryDate
    -0.63
     Appears
    -0.63
    licts
    -0.62
     periodically
    -0.61
    ilus
    -0.60
    ciplinary
    -0.58
    nis
    -0.57
     =================================
    -0.56
    gencies
    -0.56
    POSITIVE LOGITS
     nor
    1.09
     anymore
    1.07
     slightest
    0.86
     enough
    0.77
     bothered
    0.76
     any
    0.76
     anything
    0.75
     adequately
    0.75
     yesterday
    0.74
     sufficiently
    0.70
    Act Density 0.552%

    No Known Activations