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

    Neuronpedia

    INDEX
    Explanations

    repetitive and connective expressions commonly used in structured content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Innoc
    -0.15
    akte
    -0.15
    _tim
    -0.14
    odu
    -0.14
    rac
    -0.14
    ikon
    -0.14
    -INF
    -0.14
    .CreateInstance
    -0.14
    -------------</
    -0.14
    iod
    -0.14
    POSITIVE LOGITS
    ovsky
    0.18
     dil
    0.16
     Garrison
    0.15
    ismatic
    0.15
     Kane
    0.15
    ovement
    0.15
     Dil
    0.14
    izon
    0.14
     navig
    0.13
    ovit
    0.13
    Act Density 0.002%

    No Known Activations