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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific placeholder or identifier in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.72
     Canaver
    -0.70
    gew
    -0.69
     Gould
    -0.68
    vor
    -0.68
    vim
    -0.68
    ribly
    -0.68
    rolet
    -0.65
    ties
    -0.63
    athed
    -0.62
    POSITIVE LOGITS
     responders
    1.10
     Published
    1.01
     baseman
    0.87
     impressions
    0.83
     lady
    0.82
     Nations
    0.82
     Appearance
    0.81
     ancest
    0.81
     timers
    0.79
    Lady
    0.75
    Act Density 0.060%

    No Known Activations