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

    Neuronpedia

    INDEX
    Explanations

    names associated with academic qualifications and areas of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theon
    -0.08
    thal
    -0.07
    stell
    -0.07
    rahim
    -0.07
     Ger
    -0.06
    PRECATED
    -0.06
    lox
    -0.06
    zw
    -0.06
    axis
    -0.06
     liá»ĩt
    -0.06
    POSITIVE LOGITS
    oret
    0.09
    oretical
    0.07
    gger
    0.07
    aves
    0.07
    aid
    0.06
    ors
    0.06
     artificial
    0.06
    imu
    0.06
    opper
    0.06
    रत
    0.06
    Act Density 0.002%

    No Known Activations