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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and qualifications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.69
     فريبيس
    -0.67
     AssemblyCulture
    -0.66
    UserScript
    -0.56
    XtraBars
    -0.56
    rungsseite
    -0.54
     ExecuteAsync
    -0.52
    \{\\
    -0.52
    addPreferredGap
    -0.51
    TagMode
    -0.49
    POSITIVE LOGITS
     hundred
    1.38
     hundert
    1.20
    hundred
    1.05
     Hundred
    1.00
    Hundred
    1.00
    百分
    0.99
    百分之
    0.93
     completely
    0.91
     💯
    0.90
     cien
    0.86
    Act Density 0.437%

    No Known Activations