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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals named "Griffith" and "Fernando."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onyms
    -0.88
    enger
    -0.88
    ocular
    -0.83
    selves
    -0.79
    thal
    -0.75
    lished
    -0.71
    engers
    -0.69
    akable
    -0.69
    icist
    -0.69
    cule
    -0.69
    POSITIVE LOGITS
     Griffith
    0.97
    shire
    0.73
     Palmer
    0.67
     flowering
    0.66
    batch
    0.63
     Inquisition
    0.62
    haw
    0.60
     rom
    0.59
     Alonso
    0.59
    tree
    0.59
    Act Density 0.038%

    No Known Activations