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

    Neuronpedia

    INDEX
    Explanations

    terms related to meaningfulness and clarity in communication or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.54
    TagMode
    -0.48
     arrivo
    -0.47
    Гео
    -0.47
    arean
    -0.46
    GetComponent
    -0.46
    dymyr
    -0.46
    嫌疑
    -0.44
    кота
    -0.44
     encan
    -0.44
    POSITIVE LOGITS
     decent
    0.92
     meaningful
    0.83
     adequate
    0.83
     فريبيس
    0.81
     enough
    0.80
     reliable
    0.79
     reasonable
    0.79
    enough
    0.79
     vernünf
    0.79
    Hochspringen
    0.74
    Act Density 0.591%

    No Known Activations