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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Brand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.79
     attendant
    -0.78
    pmwiki
    -0.74
    urnal
    -0.69
    ancial
    -0.63
    fortunately
    -0.63
     Tsu
    -0.61
    ptoms
    -0.60
    ursion
    -0.60
     circadian
    -0.60
    POSITIVE LOGITS
    enburg
    1.20
    enberg
    0.88
    olph
    0.88
    stown
    0.84
    opher
    0.84
    ing
    0.81
    olini
    0.79
    enstein
    0.77
    haar
    0.76
    leck
    0.76
    Act Density 0.040%

    No Known Activations