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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or titles related to individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.84
    fare
    -0.77
    OFF
    -0.77
     Tayyip
    -0.73
    awa
    -0.73
    NPR
    -0.71
    oria
    -0.69
    aiden
    -0.67
    oided
    -0.66
    ãĤ®
    -0.65
    POSITIVE LOGITS
    iliary
    0.82
    cffff
    0.78
    omething
    0.70
    bats
    0.69
     bluff
    0.68
    iosyn
    0.65
    geoning
    0.65
    ly
    0.64
    esville
    0.63
    vier
    0.63
    Act Density 0.070%

    No Known Activations