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

    Neuronpedia

    INDEX
    Explanations

    academic affiliations and professional roles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ultras
    -0.76
     brut
    -0.74
     fragment
    -0.71
     undercut
    -0.69
     tram
    -0.66
     ration
    -0.66
     brawl
    -0.66
     cannibal
    -0.65
     multiplying
    -0.64
    rums
    -0.64
    POSITIVE LOGITS
    HAEL
    0.86
     Scholarship
    0.81
     Instructor
    0.78
     Elk
    0.75
    usha
    0.75
     Editor
    0.74
     Associate
    0.74
     Consult
    0.73
     McKenzie
    0.73
    maxwell
    0.72
    Act Density 0.447%

    No Known Activations