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

    Neuronpedia

    INDEX
    Explanations

    the word "all"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases emphasizing the concept of "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.66
    rive
    -0.65
    Write
    -0.61
     mathemat
    -0.61
    ritic
    -0.60
    rogens
    -0.60
    nom
    -0.60
    isol
    -0.57
    ate
    -0.56
    perm
    -0.56
    POSITIVE LOGITS
    ocating
    1.04
     sorts
    0.98
     kinds
    0.96
     sake
    0.95
    igators
    0.93
    igator
    0.88
     purposes
    0.86
    iance
    0.81
    usions
    0.78
    iances
    0.78
    Act Density 0.044%

    No Known Activations