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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    2
    -0.20
    star
    -0.20
    1
    -0.19
    7
    -0.18
    3
    -0.17
    4
    -0.17
     star
    -0.17
    u
    -0.16
    an
    -0.16
    8
    -0.15
    POSITIVE LOGITS
    ilir
    0.16
     mastur
    0.16
    GuidId
    0.15
     poil
    0.15
    ehen
    0.15
    ildenafil
    0.15
    -avatar
    0.15
    ãĥ´ãĤ£
    0.15
    ={({
    0.15
    ipar
    0.15
    Act Density 0.008%

    No Known Activations