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

    Neuronpedia

    INDEX
    Explanations

    words related to academic achievement and recognition

    oai_token-act-pair · gpt-3.5-turbo

    words related to alcohol and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.69
    llah
    -0.65
     Pwr
    -0.62
    ãģ®éŃĶ
    -0.61
     conscience
    -0.57
     tumble
    -0.57
     itch
    -0.56
    merce
    -0.56
     TAMADRA
    -0.56
    ALSE
    -0.56
    POSITIVE LOGITS
    emort
    0.99
    heed
    0.97
    uania
    0.95
    ansk
    0.92
    ttle
    0.87
    oyd
    0.85
    cious
    0.85
    achev
    0.84
    gow
    0.83
    gren
    0.81
    Act Density 0.105%

    No Known Activations