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

    Neuronpedia

    INDEX
    Explanations

    words related to physical activities and behaviors

    oai_token-act-pair · gpt-3.5-turbo

    elements associated with quotations or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Melania
    -0.76
     mast
    -0.73
     Lil
    -0.73
    otten
    -0.72
    laus
    -0.72
     Mel
    -0.70
    onut
    -0.68
    tor
    -0.68
     Melanie
    -0.67
     Hats
    -0.67
    POSITIVE LOGITS
     Q
    2.32
    Q
    2.28
     Qu
    2.23
    Qu
    2.08
    qu
    2.00
     qu
    1.95
     QU
    1.93
     q
    1.90
    QU
    1.86
    q
    1.82
    Act Density 0.302%

    No Known Activations