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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to technical specifications or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azzi
    -0.17
    irut
    -0.17
    avic
    -0.16
    æ³
    -0.16
    oleon
    -0.15
    ale
    -0.15
    .icons
    -0.14
    ilon
    -0.14
    elog
    -0.14
    ernaut
    -0.14
    POSITIVE LOGITS
    yn
    0.15
    .truth
    0.15
    yll
    0.14
    YN
    0.14
     Jub
    0.14
    enties
    0.14
    213
    0.14
    å³
    0.14
    ROID
    0.14
    826
    0.14
    Act Density 0.057%

    No Known Activations