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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ta" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.73
    رشف
    -0.72
     BoxFit
    -0.64
    fiez
    -0.61
    ModelAdmin
    -0.59
    Бахар
    -0.57
    GetKeyDown
    -0.56
    υμα
    -0.56
     ISNI
    -0.55
    ?}",
    -0.55
    POSITIVE LOGITS
    та
    1.67
     esternos
    0.86
    тала
    0.85
    findpost
    0.73
    te
    0.68
    DockStyle
    0.65
    ТА
    0.64
    тать
    0.63
    werde
    0.60
     та
    0.60
    Act Density 0.029%

    No Known Activations