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

    Neuronpedia

    INDEX
    Explanations

    references to alternative explanations or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysters
    -0.16
    -floating
    -0.16
    okes
    -0.15
    IDE
    -0.15
    aday
    -0.14
    orns
    -0.14
    allon
    -0.14
    oupon
    -0.14
    agna
    -0.13
    Inlining
    -0.13
    POSITIVE LOGITS
     words
    0.28
    words
    0.22
     respects
    0.17
     said
    0.16
     Words
    0.16
    .words
    0.16
     news
    0.16
     says
    0.15
     saying
    0.15
     cases
    0.15
    Act Density 0.018%

    No Known Activations