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

    Neuronpedia

    INDEX
    Explanations

    quotes and messages in a structured conversation

    oai_token-act-pair · gpt-3.5-turbo

    references to quotes and authorship in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.80
    aucas
    -0.78
    oulos
    -0.77
    essen
    -0.73
    hop
    -0.72
    etting
    -0.70
    LOS
    -0.70
    alore
    -0.69
     silhou
    -0.67
    otom
    -0.67
    POSITIVE LOGITS
     Originally
    1.04
     Posted
    1.04
     Quote
    0.84
     Posts
    0.79
     ·
    0.79
    Quote
    0.77
     Rating
    0.76
     Thread
    0.75
     Password
    0.74
    Posts
    0.73
    Act Density 0.043%

    No Known Activations