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

    Neuronpedia

    INDEX
    Explanations

    specific phonetic patterns or unique letter combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ches
    -0.16
    celik
    -0.15
    ormal
    -0.15
    ourcing
    -0.15
    æħ
    -0.14
    erness
    -0.14
    aving
    -0.14
     Polar
    -0.14
    addle
    -0.14
    uesta
    -0.14
    POSITIVE LOGITS
    dana
    0.14
    orsk
    0.14
    434
    0.14
    (æ°´
    0.14
     mieux
    0.13
    èĩ
    0.13
     Fletcher
    0.13
     kys
    0.13
    -validate
    0.13
     Powder
    0.13
    Act Density 0.155%

    No Known Activations