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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating certainty or resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    818
    -0.15
    utter
    -0.15
     Trev
    -0.14
    oto
    -0.14
    ley
    -0.14
     Fare
    -0.13
    207
    -0.13
     hooks
    -0.13
    808
    -0.13
    asia
    -0.13
    POSITIVE LOGITS
    deaux
    0.18
    )prepare
    0.15
    rowsable
    0.14
    /operators
    0.14
     Pascal
    0.14
    åħ¸
    0.14
    adiens
    0.14
    mae
    0.14
    AMS
    0.14
    âĨĴâĨĴ
    0.14
    Act Density 0.166%

    No Known Activations