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

    Neuronpedia

    INDEX
    Explanations

    terms related to causal relationships and statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.85
     BoxFit
    -0.77
    InputBorder
    -0.74
    RectangleBorder
    -0.73
     varandra
    -0.68
    IntoConstraints
    -0.66
    WebVitals
    -0.65
     vägen
    -0.65
    ConstraintMaker
    -0.63
     NDEBUG
    -0.62
    POSITIVE LOGITS
    ってみて
    0.72
    <bos>
    0.67
    ってみる
    0.67
    ってみました
    0.62
    nocześnie
    0.61
    そうに
    0.60
    ってみた
    0.59
    ればいい
    0.54
     "}";
    0.53
    ってください
    0.53
    Act Density 39.170%

    No Known Activations