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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing involvement or action over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orc
    -0.15
    nst
    -0.15
    üst
    -0.15
    oyo
    -0.15
    adius
    -0.14
     Cha
    -0.14
    yg
    -0.14
    ü
    -0.14
     hala
    -0.14
    abl
    -0.14
    POSITIVE LOGITS
    anio
    0.15
    antic
    0.15
    isdigit
    0.14
    æĬĺ
    0.14
    (draw
    0.14
    znam
    0.14
    ĶåĽŀ
    0.14
    éĻĨ
    0.14
    §
    0.13
    ][]
    0.13
    Act Density 0.042%

    No Known Activations