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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations

    oai_token-act-pair · gpt-3.5-turbo

    commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.65
    irie
    -0.63
     sqor
    -0.61
     scrut
    -0.58
    ãģł
    -0.58
    =#
    -0.58
    sein
    -0.58
    REDACTED
    -0.57
    ahon
    -0.57
    untarily
    -0.57
    POSITIVE LOGITS
     whose
    1.63
    whose
    1.43
     which
    1.43
     where
    1.41
     whom
    1.30
     who
    1.26
     wherein
    1.23
    which
    1.22
    where
    1.17
    who
    1.07
    Act Density 0.341%

    No Known Activations