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

    Neuronpedia

    INDEX
    Explanations

    code structure elements and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .walk
    -0.15
     VÅ¡ech
    -0.15
    terra
    -0.15
    allon
    -0.15
    ÙĪات
    -0.15
    _LAYER
    -0.14
    ram
    -0.14
    erse
    -0.14
    ple
    -0.14
    OOK
    -0.13
    POSITIVE LOGITS
     snd
    0.15
    ade
    0.14
    ACES
    0.14
    udic
    0.14
     gr
    0.13
    ãĥ«ãĥĪ
    0.13
    شب
    0.13
     iron
    0.13
     Pod
    0.13
    osy
    0.13
    Act Density 0.003%

    No Known Activations