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

    Neuronpedia

    INDEX
    Explanations

    mentions of 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
    -0.94
    IDER
    -0.78
    éĹĺ
    -0.76
    ider
    -0.74
    ppo
    -0.72
    hower
    -0.71
    iders
    -0.70
     Presbyter
    -0.70
     Methodist
    -0.68
    mith
    -0.68
    POSITIVE LOGITS
    pet
    1.11
    ertodd
    1.01
    abyte
    0.91
     pee
    0.89
     pet
    0.84
    roleum
    0.82
    apixel
    0.82
    itions
    0.81
    abytes
    0.80
    lyak
    0.80
    Act Density 0.008%

    No Known Activations