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

    Neuronpedia

    INDEX
    Explanations

    occurrences of formal writing conventions or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     profilo
    -0.72
    حياته
    -0.69
     autorytatywna
    -0.66
    帖最后由
    -0.66
    homonymie
    -0.65
    berdayakan
    -0.65
     potere
    -0.62
    ✭✭
    -0.62
    hips
    -0.61
    حياتها
    -0.60
    POSITIVE LOGITS
     gummies
    2.85
     Gummies
    2.37
     gummy
    1.22
     Audiodateien
    0.73
     pills
    0.69
     Gummi
    0.66
    Dentist
    0.63
     Knie
    0.60
    XMLSchema
    0.59
     edibles
    0.59
    Act Density 0.032%

    No Known Activations