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

    Neuronpedia

    INDEX
    Explanations

    references to pets or pet-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to pets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.77
    IDER
    -0.73
    xual
    -0.71
     PUBLIC
    -0.68
    ources
    -0.67
     doub
    -0.64
    DERR
    -0.64
    UME
    -0.63
     seeded
    -0.63
    hower
    -0.62
    POSITIVE LOGITS
    ertodd
    1.37
    abyte
    1.11
    abytes
    1.08
    pet
    1.04
    rified
    1.03
    roleum
    1.02
    itions
    0.97
    unia
    0.93
    lyak
    0.93
     pee
    0.92
    Act Density 0.026%

    No Known Activations