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

    Neuronpedia

    INDEX
    Explanations

    references to data columns in structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anvas
    -0.17
    kola
    -0.17
    redi
    -0.17
    slashes
    -0.16
    CAPE
    -0.16
    dos
    -0.16
    dong
    -0.16
    hev
    -0.15
    lashes
    -0.15
    slash
    -0.15
    POSITIVE LOGITS
    ar
    0.34
    arity
    0.25
    ists
    0.25
    wise
    0.25
    aires
    0.24
    ally
    0.21
    aire
    0.20
    Defs
    0.20
    -wise
    0.20
     headers
    0.20
    Act Density 0.020%

    No Known Activations