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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jangka
    -0.30
     COMMON
    -0.26
     elämä
    -0.25
     Life
    -0.25
     noted
    -0.24
     REPAIR
    -0.24
    calça
    -0.23
     length
    -0.23
     olisi
    -0.23
     amarillas
    -0.23
    POSITIVE LOGITS
    OGND
    0.81
     Мексичка
    0.78
     незавершена
    0.72
    RectangleBorder
    0.70
     autorytatywna
    0.69
    󠁴
    0.67
    parsedMessage
    0.66
     بيها
    0.66
    SRS
    0.65
    PDS
    0.65
    Act Density 0.805%

    No Known Activations