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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to performance metrics and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prob
    -0.16
     geil
    -0.15
    звиÑĩай
    -0.14
    äter
    -0.14
    +↵↵
    -0.14
    Ñĸк
    -0.14
    ака
    -0.14
    aleb
    -0.14
    ods
    -0.13
     Gron
    -0.13
    POSITIVE LOGITS
     negative
    0.50
     (-
    0.46
    (-
    0.44
     minus
    0.43
     Negative
    0.42
    negative
    0.39
     `-
    0.39
     [-
    0.38
    Negative
    0.38
    =-
    0.38
    Act Density 0.145%

    No Known Activations