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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate first-hand experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     b
    -0.16
    WhiteSpace
    -0.16
    æĭ¼
    -0.15
     Locker
    -0.15
    çĽij
    -0.14
    loat
    -0.14
    ály
    -0.14
    ãģķãĤī
    -0.14
    _compile
    -0.14
    ESP
    -0.14
    POSITIVE LOGITS
    ãģ°
    0.17
    Ñĥб
    0.15
    iyel
    0.15
    ho
    0.15
    _NAMESPACE
    0.14
     Dün
    0.14
    queda
    0.14
    ben
    0.14
    abel
    0.14
    ças
    0.14
    Act Density 0.034%

    No Known Activations