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

    Neuronpedia

    INDEX
    Explanations

    preferences and expressions of appreciation or desire

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

    Expressing a preference

    np_acts-logits-general · gemini-2.0-flash

    preference and desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tothe
    -0.58
    Parte
    -0.50
    {...
    -0.50
    matmul
    -0.49
    (&$
    -0.48
    setOpaque
    -0.48
    }?
    -0.47
    HIT
    -0.46
    matica
    -0.46
    lata
    -0.45
    POSITIVE LOGITS
     if
    0.89
     للمعارف
    0.83
    पया
    0.73
    rungsseite
    0.69
     дописавши
    0.67
     jika
    0.65
     wenn
    0.65
     gdyby
    0.65
    ValueStyle
    0.64
     helst
    0.64
    Act Density 0.178%

    No Known Activations