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

    Neuronpedia

    INDEX
    Explanations

    phrases highlighting different forms or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.16
    ãģ¡ãģ¯
    -0.14
    inya
    -0.14
    alam
    -0.14
    chn
    -0.14
     cooldown
    -0.14
     Row
    -0.14
     Král
    -0.14
    astes
    -0.14
    esa
    -0.13
    POSITIVE LOGITS
    weise
    0.16
    rame
    0.16
    tras
    0.15
    quot
    0.15
    urum
    0.15
    许
    0.14
    readcr
    0.14
    otope
    0.14
    Gram
    0.13
    agate
    0.13
    Act Density 0.034%

    No Known Activations