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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal admission or honesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Expressions of honesty or admission

    np_acts-logits-general · gemini-2.0-flash

    honesty and admission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.64
     typelib
    -0.62
    webElementXpaths
    -0.62
     للمعارف
    -0.57
    Personensuche
    -0.56
     المعيارى
    -0.56
     <<<<<<<<<<<<<<
    -0.56
     Photocase
    -0.54
    ंदीखरीदारी
    -0.54
    曖昧さ回避
    -0.51
    POSITIVE LOGITS
    正直
    0.77
     admit
    0.75
    Honestly
    0.71
     Honestly
    0.69
     frankly
    0.69
     honestly
    0.68
    mittedly
    0.67
    Frankly
    0.65
    honestly
    0.65
     admits
    0.64
    Act Density 0.210%

    No Known Activations