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

    Neuronpedia

    INDEX
    Explanations

    terms related to specifications and statements in legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addGap
    -0.65
     ویکی‌پدیای
    -0.65
    djangoproject
    -0.62
     Paradis
    -0.61
    HomeAsUp
    -0.60
    ISupport
    -0.60
    anguard
    -0.58
     Verdun
    -0.58
    shadowOffset
    -0.57
    ondag
    -0.57
    POSITIVE LOGITS
     InputDecoration
    0.96
     stated
    0.89
    explicit
    0.78
     bezeichneter
    0.75
    Enumerated
    0.74
     explí
    0.73
     specifies
    0.73
     Mentions
    0.73
    pecified
    0.72
     specify
    0.71
    Act Density 0.336%

    No Known Activations