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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to requirements and obligations

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

    following auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    absolutely cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.90
    anskje
    -0.88
     $_"
    -0.88
    
    -0.83
     IBRARY
    -0.82
    VERTISEMENT
    -0.81
    __":
    -0.81
     BRARY
    -0.79
    Bronnen
    -0.79
     Ведь
    -0.79
    POSITIVE LOGITS
     NOT
    1.13
     absolutely
    0.97
     CANNOT
    0.95
    NOT
    0.90
     ABSOL
    0.89
     THIS
    0.88
     absolutamente
    0.87
    absolutely
    0.86
    THIS
    0.82
     NO
    0.81
    Act Density 0.395%

    No Known Activations