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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated units of measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    831
    -0.17
    loat
    -0.16
    egral
    -0.16
    94
    -0.14
    arsi
    -0.14
    enne
    -0.14
    ats
    -0.14
    pom
    -0.14
     exactly
    -0.14
    977
    -0.13
    POSITIVE LOGITS
    350
    0.34
    150
    0.30
    800
    0.28
    250
    0.28
    300
    0.28
    450
    0.27
    400
    0.27
    750
    0.26
    700
    0.26
    120
    0.26
    Act Density 0.224%

    No Known Activations