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

    Neuronpedia

    INDEX
    Explanations

    references to parameters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernet
    -0.16
    erman
    -0.16
    eltas
    -0.15
    arga
    -0.15
     наÑģелениÑı
    -0.15
    ermann
    -0.15
    ICLES
    -0.15
    ards
    -0.15
    chner
    -0.15
    ness
    -0.14
    POSITIVE LOGITS
    etrize
    0.19
    etric
    0.18
    edics
    0.16
    ised
    0.16
    oled
    0.16
    OutOfRangeException
    0.15
    ization
    0.15
    atic
    0.15
    agnetic
    0.15
    ascus
    0.15
    Act Density 0.036%

    No Known Activations