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

    Neuronpedia

    INDEX
    Explanations

    references to missed opportunities or alternative choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potentiality or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilty
    -0.73
    plex
    -0.65
    utor
    -0.59
    gencies
    -0.57
    ele
    -0.57
     Blitz
    -0.56
    istent
    -0.56
    ving
    -0.54
    bert
    -0.53
     Kis
    -0.53
    POSITIVE LOGITS
     feas
    1.06
     easily
    0.99
    ivably
    0.99
     conce
    0.92
    ħĭ
    0.86
     possibly
    0.84
    nesota
    0.77
     potentially
    0.77
     alternatively
    0.73
    heard
    0.72
    Act Density 0.139%

    No Known Activations