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

    Neuronpedia

    INDEX
    Explanations

    cultural references and character names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grimm
    -0.15
    ULO
    -0.15
    泡
    -0.15
    iffe
    -0.15
    ardi
    -0.14
    Streamer
    -0.14
    isser
    -0.14
    .SC
    -0.14
    GLenum
    -0.14
     Stealth
    -0.14
    POSITIVE LOGITS
     mole
    0.20
    alte
    0.20
     Mix
    0.20
    atl
    0.20
    apan
    0.19
     alte
    0.18
    Cop
    0.18
    hua
    0.18
     indigenous
    0.17
    ahu
    0.17
    Act Density 0.034%

    No Known Activations