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

    Neuronpedia

    INDEX
    Explanations

    numerical data and values related to scientific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     last
    -0.57
    ↵↵
    -0.52
    Jeografia
    -0.50
     Man
    -0.50
     
    -0.48
     wo
    -0.48
     man
    -0.47
     сно
    -0.47
    megap
    -0.46
     What
    -0.46
    POSITIVE LOGITS
     Houſe
    0.99
     Shakspeare
    0.88
     Efq
    0.88
     vidare
    0.84
     Anſ
    0.82
     umgekehrt
    0.80
    BeginInit
    0.79
    ✨:
    0.79
    UnusedPrivate
    0.77
    leyebilirsiniz
    0.76
    Act Density 0.136%

    No Known Activations