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

    Neuronpedia

    INDEX
    Explanations

    personal opinions and reactions in a conversational context

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Âł
    -0.54
    arist
    -0.52
     Cells
    -0.50
     âī¡
    -0.50
     Material
    -0.48
    akeru
    -0.47
    WAR
    -0.47
    arak
    -0.45
     «
    -0.45
     Âł
    -0.44
    POSITIVE LOGITS
    .'"
    0.81
    .")
    0.76
    !'"
    0.72
    )."
    0.72
     âĢ¦"
    0.71
    '."
    0.64
    ."
    0.64
    }"
    0.60
    ]."
    0.59
    '"
    0.59
    Act Density 0.785%

    No Known Activations