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

    Neuronpedia

    INDEX
    Explanations

    references to systemic instability or breaches in ethical norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Something is failing or ending

    np_acts-logits-general · gemini-2.0-flash

    things breaking down or collapsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.72
    <bos>
    -0.67
     utafitiHapana
    -0.67
     himſelf
    -0.66
     pleaſure
    -0.62
    endwhile
    -0.60
     purpoſe
    -0.60
    出版年
    -0.59
     fusca
    -0.58
    Vidite
    -0.58
    POSITIVE LOGITS
     collapse
    1.43
     crumbling
    1.35
     breakdown
    1.28
     collapses
    1.27
     collapsing
    1.27
     crumble
    1.24
     breaking
    1.22
     crumbled
    1.19
     collapsed
    1.17
     Collapse
    1.15
    Act Density 0.587%

    No Known Activations