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

    Neuronpedia

    INDEX
    Explanations

    references to a specific family name

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific family name with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANC
    -0.75
    ANCE
    -0.71
    scape
    -0.70
    ANA
    -0.70
    REL
    -0.69
    RW
    -0.68
    zai
    -0.67
    âĸ¬
    -0.66
    BIT
    -0.66
    gan
    -0.63
    POSITIVE LOGITS
    hift
    0.97
    umps
    0.93
    ules
    0.79
    manship
    0.78
    hooting
    0.77
    paces
    0.75
    peed
    0.75
    uge
    0.74
    etsk
    0.74
    poons
    0.74
    Act Density 0.011%

    No Known Activations