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

    Neuronpedia

    INDEX
    Explanations

    specific terms and concepts related to performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dafx
    -0.74
     surla
    -0.73
     ब्रेकडाउन
    -0.69
    ⟬
    -0.60
     препратки
    -0.60
     Мексичка
    -0.59
     ſch
    -0.59
    出版年
    -0.57
     Administrativna
    -0.54
     Paglinawan
    -0.54
    POSITIVE LOGITS
     and
    0.39
     greatly
    0.37
    极了
    0.34
     importar
    0.34
     only
    0.34
     contactez
    0.33
     préfé
    0.32
     among
    0.31
     variés
    0.31
     ndani
    0.31
    Act Density 1.079%

    No Known Activations