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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant milestones or historical firsts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¬
    -0.16
    æĻ®
    -0.15
    endo
    -0.14
    ovie
    -0.14
     Variation
    -0.14
    oola
    -0.13
    ovic
    -0.13
    332
    -0.13
    庫
    -0.13
    UTH
    -0.13
    POSITIVE LOGITS
    defer
    0.16
    iger
    0.15
     deferred
    0.15
    782
    0.15
    git
    0.15
     McKenzie
    0.14
    ableView
    0.14
    linky
    0.14
     ending
    0.14
     defer
    0.14
    Act Density 0.068%

    No Known Activations