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

    Neuronpedia

    INDEX
    Explanations

    phrases related to notable events or specifics such as dates, locations, and names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stonewall" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.80
    OPLE
    -0.75
    REDACTED
    -0.73
    CONCLUS
    -0.72
    VIS
    -0.64
     CIS
    -0.64
     operating
    -0.64
     NEC
    -0.63
    chance
    -0.62
     Fract
    -0.62
    POSITIVE LOGITS
    onew
    1.12
    alling
    0.97
    eties
    0.95
    alled
    0.89
    ety
    0.87
    ield
    0.86
    izons
    0.84
    asser
    0.84
    ´
    0.83
    angular
    0.83
    Act Density 0.010%

    No Known Activations