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

    Neuronpedia

    INDEX
    Explanations

    words indicating capability or performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WindowConstants
    -0.76
     Winaray
    -0.76
    ThroughAttribute
    -0.72
     }^{[
    -0.72
    ifrance
    -0.72
    힣
    -0.70
    [^
    -0.70
    assium
    -0.70
    Σε
    -0.69
     printemps
    -0.68
    POSITIVE LOGITS
     of
    1.50
     aware
    0.84
    dientemente
    0.81
    SOUNDBITE
    0.79
     apesar
    0.75
    agisse
    0.75
    Aware
    0.73
     bisogno
    0.72
     behulp
    0.72
    Beware
    0.71
    Act Density 1.064%

    No Known Activations