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

    Neuronpedia

    INDEX
    Explanations

    underscores and variables in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slut
    -0.19
    avage
    -0.17
    éf
    -0.16
    .fn
    -0.16
    ctr
    -0.15
    ities
    -0.15
     Tra
    -0.14
    cctor
    -0.14
    Enumerable
    -0.14
    837
    -0.13
    POSITIVE LOGITS
    ippet
    0.15
    erview
    0.15
    åĪij
    0.15
    Ñĩки
    0.15
    ptal
    0.15
    erken
    0.15
    ISCO
    0.14
    داÙħ
    0.14
     kuk
    0.14
    ird
    0.14
    Act Density 0.004%

    No Known Activations