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

    Neuronpedia

    INDEX
    Explanations

    references to domestic animals, particularly pets

    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
    xual
    -0.80
    éĹĺ
    -0.79
    IDER
    -0.76
    kefeller
    -0.75
     Methodist
    -0.74
    hower
    -0.71
     doub
    -0.68
     seeded
    -0.67
    ider
    -0.67
    mith
    -0.67
    POSITIVE LOGITS
    ertodd
    1.06
    pet
    1.02
    abyte
    1.01
     pee
    0.97
    abytes
    0.93
    lyak
    0.87
    rified
    0.82
     pets
    0.78
    apixel
    0.78
    WOR
    0.78
    Act Density 0.011%

    No Known Activations