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

    Neuronpedia

    INDEX
    Explanations

    verbs related to accountability

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply accountability and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.62
     NOT
    -0.60
     largeDownload
    -0.59
     Emin
    -0.59
     Macintosh
    -0.57
    asionally
    -0.55
     assorted
    -0.54
     ALSO
    -0.54
     Pathfinder
    -0.54
     ALWAYS
    -0.53
    POSITIVE LOGITS
     anymore
    1.47
     nor
    1.36
     slightest
    1.14
    yet
    0.90
    enough
    0.84
     any
    0.83
     anything
    0.80
     necessarily
    0.79
     enough
    0.79
     whatsoever
    0.76
    Act Density 0.666%

    No Known Activations