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

    Neuronpedia

    INDEX
    Explanations

    references to bodily functions and related humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iry
    -0.17
     Beaut
    -0.15
    .Serial
    -0.14
    ovsky
    -0.14
    czy
    -0.14
     Series
    -0.14
     reflection
    -0.14
     reflections
    -0.14
    emple
    -0.14
    itt
    -0.14
    POSITIVE LOGITS
    รà¸Ķ
    0.22
    åľ
    0.15
    ìĭ
    0.14
    obsolete
    0.14
    edback
    0.14
    edReader
    0.14
    AXB
    0.14
    ewan
    0.14
    عا
    0.14
    hawk
    0.14
    Act Density 0.080%

    No Known Activations