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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison and evaluation of characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.15
    ascript
    -0.14
    onta
    -0.14
    มà¸Ń
    -0.14
    Ñģлов
    -0.14
    ugu
    -0.14
     JsonRequestBehavior
    -0.14
    utar
    -0.14
    ahoo
    -0.14
    hek
    -0.13
    POSITIVE LOGITS
     strong
    1.00
    strong
    0.87
     Strong
    0.87
     strength
    0.86
    Strong
    0.82
     stronger
    0.78
    strength
    0.77
    -strong
    0.77
     Strength
    0.76
     strongest
    0.73
    Act Density 0.304%

    No Known Activations