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

    Neuronpedia

    INDEX
    Explanations

    references to accuracy and correctness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iphy
    -0.15
    PHY
    -0.15
    forge
    -0.15
     sik
    -0.14
    vit
    -0.14
     ki
    -0.14
    iesel
    -0.14
    ury
    -0.14
    vat
    -0.13
    å©
    -0.13
    POSITIVE LOGITS
    itude
    0.16
    åĩĨ
    0.15
    æħİ
    0.15
    bow
    0.14
    IVEN
    0.14
    empo
    0.14
    ivant
    0.14
    sed
    0.14
    íĭ°
    0.14
    _rwlock
    0.14
    Act Density 0.015%

    No Known Activations