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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with the concept of positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tiles
    -0.15
    importe
    -0.15
    .AutoScaleMode
    -0.15
    sburg
    -0.15
    íĻĶ를
    -0.14
    trip
    -0.14
    íĻĶ
    -0.14
    istrovstvÃŃ
    -0.14
    पत
    -0.14
    uzz
    -0.14
    POSITIVE LOGITS
    itivity
    0.27
    ITIVE
    0.27
    sum
    0.26
    itives
    0.26
    session
    0.23
    lednÃŃ
    0.23
    SESSION
    0.23
    idon
    0.22
    ynomial
    0.22
    itive
    0.22
    Act Density 0.011%

    No Known Activations