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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "all" is specifically emphasized

    oai_token-act-pair · gpt-3.5-turbo

    the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDS
    -0.68
    EStream
    -0.66
    lav
    -0.66
    SHIP
    -0.62
    aminer
    -0.60
    grad
    -0.60
    fman
    -0.59
    nom
    -0.59
    abwe
    -0.58
    cept
    -0.57
    POSITIVE LOGITS
    ocating
    1.20
    igator
    0.97
    ocated
    0.96
    igators
    0.96
     sorts
    0.95
     kinds
    0.93
    ocate
    0.92
    iances
    0.87
    ocation
    0.85
    usion
    0.84
    Act Density 0.124%

    No Known Activations