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

    Neuronpedia

    INDEX
    Explanations

    numerical percentages or statistics

    oai_token-act-pair · gpt-3.5-turbo

    percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pecially
    -0.83
    etheless
    -0.81
     compan
    -0.78
     neighb
    -0.76
    itiz
    -0.74
     brace
    -0.74
    uras
    -0.74
     shaped
    -0.74
     compr
    -0.73
     lett
    -0.72
    POSITIVE LOGITS
    -+
    0.90
    %)
    0.78
    %
    0.76
    %-
    0.74
    +)
    0.72
     Mehran
    0.72
    âĨij
    0.71
     ABV
    0.69
    -|
    0.68
     Ibid
    0.68
    Act Density 0.049%

    No Known Activations