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

    Neuronpedia

    INDEX
    Explanations

    references or citations in academic or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ä©
    -0.16
    beros
    -0.14
    arb
    -0.14
    кеÑĤ
    -0.13
    vation
    -0.13
     @(
    -0.13
    ôi
    -0.13
    ôn
    -0.13
    plex
    -0.13
    ules
    -0.13
    POSITIVE LOGITS
    alias
    0.23
    [][]
    0.19
    ads
    0.17
    [][
    0.17
    iland
    0.15
    ersions
    0.15
    elier
    0.15
    elif
    0.15
    erval
    0.14
     Hers
    0.14
    Act Density 0.007%

    No Known Activations