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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax elements related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acock
    -0.15
    umat
    -0.15
     paramet
    -0.14
    ocate
    -0.14
    .diag
    -0.14
     Chunk
    -0.13
    ofire
    -0.13
     phá
    -0.13
    Ñģлов
    -0.13
    abcdefghijklmnop
    -0.13
    POSITIVE LOGITS
    lán
    0.15
    bero
    0.15
    aph
    0.15
     backing
    0.15
    lan
    0.14
     Starr
    0.14
    rels
    0.14
     beden
    0.14
    çľ
    0.14
    erchant
    0.13
    Act Density 0.080%

    No Known Activations