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

    Neuronpedia

    INDEX
    Explanations

    words related to physical locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to "mills" or related terminology in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Malays
    -0.77
    oÄŁ
    -0.76
    TAG
    -0.70
    lia
    -0.68
     affili
    -0.67
     Bulgar
    -0.66
    bal
    -0.65
     prime
    -0.64
    Barn
    -0.63
    members
    -0.63
    POSITIVE LOGITS
    iard
    1.02
    inger
    0.97
    sburg
    0.96
    hops
    0.86
    chool
    0.85
    espie
    0.84
    uminati
    0.83
    ills
    0.82
    ibrary
    0.82
    avascript
    0.80
    Act Density 0.005%

    No Known Activations