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

    Neuronpedia

    INDEX
    Explanations

    numeric values that likely represent data points or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eum
    -0.16
     Cabinet
    -0.16
    roperties
    -0.16
    vale
    -0.15
    -br
    -0.15
     Ley
    -0.15
    ียà¸ĩ
    -0.15
     Lloyd
    -0.15
    ounding
    -0.15
    é±
    -0.14
    POSITIVE LOGITS
     Roose
    0.15
    _atomic
    0.15
    629
    0.15
     cord
    0.14
    442
    0.14
    æĹı
    0.14
     Thornton
    0.13
    662
    0.13
    147
    0.13
    banana
    0.13
    Act Density 0.032%

    No Known Activations