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

    Neuronpedia

    INDEX
    Explanations

    the word "All" followed by other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abwe
    -0.73
    EStream
    -0.72
    rir
    -0.71
     tremend
    -0.71
    aminer
    -0.67
     sight
    -0.66
    isoft
    -0.65
     horizon
    -0.65
    existent
    -0.64
    icable
    -0.64
    POSITIVE LOGITS
    ocate
    1.11
    owed
    1.09
    iance
    1.09
    owing
    1.06
    iances
    1.02
    ocated
    0.99
    ocation
    0.97
    igator
    0.96
    ocating
    0.93
    ergic
    0.93
    Act Density 0.049%

    No Known Activations