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

    Neuronpedia

    INDEX
    Explanations

    the phrase "After all"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lav
    -0.71
     Kamp
    -0.63
    cept
    -0.62
    nom
    -0.60
     Schwe
    -0.58
    fman
    -0.58
    utsche
    -0.57
    eele
    -0.57
    grad
    -0.57
    ritic
    -0.56
    POSITIVE LOGITS
    ocating
    1.06
    igator
    1.00
    igators
    0.97
    iances
    0.93
     kinds
    0.90
    iance
    0.89
     sorts
    0.87
    uding
    0.84
    udes
    0.83
    owing
    0.80
    Act Density 0.140%

    No Known Activations