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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating levels or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibbon
    -0.17
    idar
    -0.15
    ìĪľ
    -0.14
    grounds
    -0.14
     Grund
    -0.14
    apo
    -0.14
    ãĤ§
    -0.14
    INTR
    -0.13
    _ATOM
    -0.13
    oral
    -0.13
    POSITIVE LOGITS
    unal
    0.15
    atos
    0.15
    hof
    0.14
    acer
    0.14
     rer
    0.14
     Klo
    0.14
    all
    0.14
     Ott
    0.14
    ldb
    0.14
    ais
    0.14
    Act Density 0.047%

    No Known Activations