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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akan
    -0.15
    atica
    -0.14
    aise
    -0.14
    isk
    -0.14
    52
    -0.14
    dle
    -0.14
    ìķĦìĦľ
    -0.13
    nik
    -0.13
     zor
    -0.13
    847
    -0.13
    POSITIVE LOGITS
    ÅĽcie
    0.16
    Arena
    0.16
    olders
    0.15
    izia
    0.15
    ATUS
    0.15
     ucwords
    0.14
    igator
    0.14
    íģ¼
    0.14
    strup
    0.14
    sword
    0.14
    Act Density 0.022%

    No Known Activations