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

    Neuronpedia

    INDEX
    Explanations

    words related to dialogues or conversations

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences or anecdotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "!
    -0.82
    "))
    -0.80
    !",
    -0.75
    ")
    -0.73
    "),
    -0.72
    ").
    -0.71
    ");
    -0.71
    .")
    -0.70
    !".
    -0.67
    othal
    -0.63
    POSITIVE LOGITS
    cause
    0.78
    Dialogue
    0.76
    entimes
    0.76
     mathemat
    0.75
    âĢij
    0.75
    laughter
    0.74
    ----
    0.72
    ofi
    0.69
    aida
    0.69
    laughs
    0.67
    Act Density 0.909%

    No Known Activations