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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and identifiers in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byname
    -0.18
    onte
    -0.16
    ÅĽ
    -0.16
    etty
    -0.15
    anford
    -0.15
     butt
    -0.15
    hardt
    -0.14
    .nl
    -0.14
     lap
    -0.14
     Fet
    -0.14
    POSITIVE LOGITS
    ะ
    0.20
    asher
    0.14
    IZES
    0.14
    206
    0.14
     èij
    0.13
    IsValid
    0.13
    beit
    0.13
    ä¼ı
    0.13
    лада
    0.13
    ctica
    0.13
    Act Density 0.040%

    No Known Activations