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

    Neuronpedia

    INDEX
    Explanations

    references to writing instruments like 'pen'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "pen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.78
    ndum
    -0.73
    ONEY
    -0.69
    ONSORED
    -0.69
    IELD
    -0.65
    ģĸ
    -0.62
    OST
    -0.62
    rians
    -0.62
     spores
    -0.61
     Athe
    -0.59
    POSITIVE LOGITS
    ultimate
    1.45
    itent
    1.41
    cil
    1.16
    manship
    1.15
    insula
    1.15
    elope
    1.09
    cill
    1.01
    nington
    0.97
    ning
    0.95
    alties
    0.91
    Act Density 0.017%

    No Known Activations