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

    Neuronpedia

    INDEX
    Explanations

    the word "exactly" and phrases indicating precision or specific values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸ķร
    -0.15
    ilan
    -0.15
    imenti
    -0.15
    ABS
    -0.14
    añ
    -0.14
    /logging
    -0.14
    atz
    -0.14
    ìķ¡
    -0.14
     crew
    -0.14
    ture
    -0.13
    POSITIVE LOGITS
    eyen
    0.18
    enes
    0.16
    idge
    0.15
    nest
    0.15
    utch
    0.15
    uta
    0.15
    obel
    0.14
    asher
    0.14
    sst
    0.14
     اÙĦÙĨÙĩ
    0.13
    Act Density 0.008%

    No Known Activations