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

    Neuronpedia

    INDEX
    Explanations

    elements related to training or instructional tools and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yro
    -0.16
    amental
    -0.15
    indi
    -0.14
    addir
    -0.14
    ersh
    -0.14
    mdir
    -0.14
    Ross
    -0.13
    erras
    -0.13
    á»Ń
    -0.13
     Jenner
    -0.13
    POSITIVE LOGITS
    zan
    0.16
     review
    0.16
    inel
    0.15
    lip
    0.15
    aton
    0.14
    eldon
    0.14
    DBG
    0.14
     pracy
    0.14
     assort
    0.14
    -review
    0.14
    Act Density 0.156%

    No Known Activations