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

    Neuronpedia

    INDEX
    Explanations

    phrases related to capability and assistance

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

    can followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.61
    GEBURTSDATUM
    -0.53
     nahilalakip
    -0.52
    webElementXpaths
    -0.50
    ItemBackground
    -0.49
    請繼續往下閱讀
    -0.48
     mijne
    -0.47
    Portale
    -0.47
    AutoScaleMode
    -0.47
     >=",
    -0.47
    POSITIVE LOGITS
     also
    0.45
     Ansari
    0.42
     Rasulullah
    0.40
     Woodford
    0.39
     Dine
    0.38
    krä
    0.38
     Cambio
    0.38
     informed
    0.38
     assisted
    0.37
     delivered
    0.37
    Act Density 0.017%

    No Known Activations