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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific pronouns and references to individuals or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seah
    -0.68
     Ballard
    -0.65
    hap
    -0.64
    detail
    -0.60
     Hok
    -0.59
     Credits
    -0.57
     juven
    -0.56
    icative
    -0.56
     Atkins
    -0.55
    Week
    -0.54
    POSITIVE LOGITS
     wont
    1.12
     didnt
    0.95
     doesnt
    0.91
     dont
    0.86
    'll
    0.82
     cant
    0.81
     would
    0.79
     should
    0.78
     will
    0.76
     MUST
    0.76
    Act Density 0.235%

    No Known Activations