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

    Neuronpedia

    INDEX
    Explanations

    legal and regulatory terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or breaks in sentences, often indicating pauses or omitted information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.81
    Ĭ±
    -0.71
    gling
    -0.67
    ãĥ«
    -0.65
    ãĤ¶
    -0.64
     carp
    -0.64
    aceous
    -0.64
     Elys
    -0.63
     fishes
    -0.63
     Ribbon
    -0.62
    POSITIVE LOGITS
     ,"
    0.85
    .,"
    0.80
    eas
    0.79
    among
    0.79
     âĢİ
    0.78
     ."
    0.76
    Judge
    0.76
    FLAG
    0.76
    Deal
    0.74
    where
    0.73
    Act Density 0.038%

    No Known Activations