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

    Neuronpedia

    INDEX
    Explanations

    statements that involve personal opinions or critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements attributed to people

    np_acts-logits-general · gemini-2.0-flash

    say or said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CellStyle
    -0.44
    interopRequire
    -0.43
     оригіналу
    -0.42
    ست
    -0.42
    RenderAtEndOf
    -0.41
    ganj
    -0.41
    mű
    -0.40
     sein
    -0.40
     الاطلاع
    -0.40
    imit
    -0.39
    POSITIVE LOGITS
     say
    1.38
     said
    1.29
     saying
    1.28
     SAY
    1.23
    Say
    1.20
    said
    1.20
     Say
    1.18
    say
    1.18
     says
    1.18
     Said
    1.16
    Act Density 0.183%

    No Known Activations