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

    Neuronpedia

    INDEX
    Explanations

    symbols or special characters that indicate formatting or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĴĥ
    -0.14
     заг
    -0.13
    ÙĦÛĮسÛĮ
    -0.12
    aceutical
    -0.12
     Agency
    -0.12
    èĬ³
    -0.12
    onitor
    -0.12
    ê°IJ
    -0.12
     Giám
    -0.12
    幸ç¦ı
    -0.12
    POSITIVE LOGITS
     Fun
    0.32
     Shot
    0.26
     kar
    0.26
     martial
    0.25
     kata
    0.25
     Kata
    0.25
    Fun
    0.24
     Kar
    0.24
     Kick
    0.24
     Martial
    0.24
    Act Density 0.001%

    No Known Activations