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

    Neuronpedia

    INDEX
    Explanations

    references to narratives or storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.16
    xing
    -0.15
    ackers
    -0.15
    pir
    -0.15
    'er
    -0.14
    aber
    -0.14
    kart
    -0.14
    zig
    -0.14
     troubled
    -0.13
    FRING
    -0.13
    POSITIVE LOGITS
    book
    0.17
    books
    0.17
     болезни
    0.16
    istical
    0.15
    hood
    0.15
    istically
    0.14
    üb
    0.14
    allback
    0.14
    boarding
    0.14
    DH
    0.14
    Act Density 0.046%

    No Known Activations