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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inati
    -0.16
    mare
    -0.15
     Verm
    -0.15
    èĬ¯
    -0.14
    prises
    -0.14
    èĩ£
    -0.14
    istas
    -0.14
    ersistent
    -0.13
     اÙĦØ«
    -0.13
    vn
    -0.13
    POSITIVE LOGITS
    onder
    0.15
    tring
    0.14
     bang
    0.14
     Sl
    0.14
    chie
    0.14
    iseum
    0.14
    íĥĿ
    0.14
    asto
    0.13
     Punch
    0.13
    etal
    0.13
    Act Density 0.005%

    No Known Activations