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

    Neuronpedia

    INDEX
    Explanations

    questions expressing curiosity or concern about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -strip
    -0.19
    terdam
    -0.16
    erland
    -0.16
    Strip
    -0.15
     Strip
    -0.15
    -addons
    -0.15
    illes
    -0.14
    cum
    -0.14
    _strip
    -0.14
     strip
    -0.14
    POSITIVE LOGITS
     so
    0.18
     tão
    0.15
     TextAlign
    0.14
     suddenly
    0.14
     everyone
    0.14
     вдÑĢÑĥг
    0.14
    antha
    0.14
    /how
    0.14
     tolik
    0.13
    arlar
    0.13
    Act Density 0.068%

    No Known Activations