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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or symbols associated with data, likely indicating lists or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOCTYPE
    -0.92
    '},
    -0.77
     AssemblyCulture
    -0.74
    contentLoaded
    -0.72
    GEBURTSDATUM
    -0.69
    LLocation
    -0.69
    ratto
    -0.69
    featureID
    -0.69
    InjectAttribute
    -0.69
     بيها
    -0.68
    POSITIVE LOGITS
    ↵↵↵↵
    0.66
    ↵↵↵↵↵
    0.65
    ↵↵↵
    0.60
    ↵↵↵↵↵↵
    0.59
    ↵↵↵↵↵↵↵↵
    0.56
    noindent
    0.56
    <strong>
    0.54
    <h2>
    0.54
    ↵↵↵↵↵↵↵
    0.53
     pochette
    0.53
    Act Density 0.304%

    No Known Activations