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

    Neuronpedia

    INDEX
    Explanations

    specific adjectives and nouns that describe qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -0.73
     Roskov
    -0.71
     Bono
    -0.67
    WebpackPlugin
    -0.63
    Kjelder
    -0.62
    MigrationBuilder
    -0.60
    haustible
    -0.60
    omiast
    -0.59
     communists
    -0.59
     Cornish
    -0.58
    POSITIVE LOGITS
     some
    0.80
    PerformLayout
    0.75
    some
    0.73
    SOME
    0.70
     SOME
    0.69
    Some
    0.68
     Some
    0.65
     nahilalakip
    0.63
    hyrchwyd
    0.58
    UTERS
    0.57
    Act Density 0.051%

    No Known Activations