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

    Neuronpedia

    INDEX
    Explanations

    dotted file paths or references to programming structure elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.87
     nakalista
    -0.85
    abestanden
    -0.80
    isContained
    -0.77
    LookAnd
    -0.75
    StructEnd
    -0.75
     propOrder
    -0.74
    complexContent
    -0.71
    Hauptartikel
    -0.71
    IsContent
    -0.70
    POSITIVE LOGITS
     /\.(
    0.84
     /\.
    0.83
     finitely
    0.66
    󠁢
    0.65
     comuna
    0.63
    fasterxml
    0.60
    [--
    0.57
    kfree
    0.55
     Shy
    0.55
     hemorr
    0.54
    Act Density 0.030%

    No Known Activations