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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĢ
    -0.16
    velt
    -0.15
    ÑĢеÑħ
    -0.15
    kening
    -0.15
    lcd
    -0.14
    lbrace
    -0.14
    atus
    -0.13
     cazzo
    -0.13
    getBytes
    -0.13
    оÑħ
    -0.13
    POSITIVE LOGITS
     few
    0.86
    few
    0.70
     Few
    0.68
    Few
    0.65
     couple
    0.57
     handful
    0.52
     FE
    0.47
     paar
    0.46
     quelques
    0.45
     fewer
    0.44
    Act Density 0.176%

    No Known Activations