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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Gen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auldron
    -0.75
     lod
    -0.75
    antha
    -0.73
     "$:/
    -0.72
    jar
    -0.71
     trough
    -0.71
     damp
    -0.69
     agitation
    -0.68
    olas
    -0.66
    rame
    -0.65
    POSITIVE LOGITS
     Gen
    3.91
    Gen
    2.80
     GEN
    2.08
     gen
    1.94
    gen
    1.73
    GEN
    1.66
     Generation
    1.46
     Gene
    1.38
     General
    1.37
     Gener
    1.36
    Act Density 0.010%

    No Known Activations