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

    Neuronpedia

    INDEX
    Explanations

    numeric identifiers or enumerations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.96
     onOptions
    -0.85
    saraba
    -0.79
     ddelweddau
    -0.76
    ngdoc
    -0.73
     cdti
    -0.73
    deelte
    -0.71
    談社
    -0.69
    Controllo
    -0.69
     betweenstory
    -0.69
    POSITIVE LOGITS
    1
    0.53
    subsection
    0.50
     Q
    0.49
     #
    0.49
     дописавши
    0.47
    ire
    0.47
    AG
    0.47
    enumerate
    0.47
     q
    0.46
    rfloor
    0.46
    Act Density 0.507%

    No Known Activations