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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and brand names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific companies and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspecified
    -0.78
    erness
    -0.60
     ident
    -0.58
    ensibly
    -0.57
     facet
    -0.56
     foul
    -0.55
     sill
    -0.54
     circumstance
    -0.54
     faintly
    -0.54
     disciplinary
    -0.53
    POSITIVE LOGITS
     etc
    0.99
     or
    0.77
    etc
    0.76
    uggest
    0.75
    rimp
    0.72
    ortex
    0.65
    ADRA
    0.63
     thrive
    0.62
    bler
    0.62
    okia
    0.62
    Act Density 0.402%

    No Known Activations