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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to performance and collaborative creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ording
    -0.18
    onom
    -0.17
    esium
    -0.15
    ugh
    -0.14
    æĥł
    -0.14
    ontent
    -0.14
    leDb
    -0.14
    ساÙĨÛĮ
    -0.14
    lex
    -0.14
    ingo
    -0.14
    POSITIVE LOGITS
     expression
    0.18
    Roll
    0.17
     Expression
    0.17
     rule
    0.16
    Expression
    0.16
    rule
    0.16
     RULE
    0.16
     Roll
    0.16
     Role
    0.16
    roller
    0.15
    Act Density 0.012%

    No Known Activations