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

    Neuronpedia

    INDEX
    Explanations

    references to a specific name - "Clark"

    oai_token-act-pair · gpt-3.5-turbo

    the token that indicates the end of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    choes
    -0.82
    urity
    -0.73
    orescence
    -0.70
    urized
    -0.69
    ño
    -0.69
    λ
    -0.69
    req
    -0.69
    gered
    -0.69
    gur
    -0.68
    htar
    -0.67
    POSITIVE LOGITS
     Kent
    0.97
    ston
    0.94
    stown
    0.93
     Ashton
    0.85
    obyl
    0.84
    icum
    0.81
    istic
    0.77
    istically
    0.77
    nect
    0.77
    istics
    0.76
    Act Density 0.034%

    No Known Activations