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

    Neuronpedia

    INDEX
    Explanations

    numeric identifiers and references in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cancelable
    -0.15
    illard
    -0.15
    ixo
    -0.15
    ISS
    -0.14
    asks
    -0.14
    eka
    -0.14
    anki
    -0.14
    .chars
    -0.13
    eldon
    -0.13
    jal
    -0.13
    POSITIVE LOGITS
    ieves
    0.17
    ãĥ¼ãĥIJ
    0.16
    ewe
    0.16
    ives
    0.15
    ãĥ
    0.15
    inski
    0.14
     ----------------------------------------------------------------------------↵
    0.14
    erokee
    0.13
    ypad
    0.13
    796
    0.13
    Act Density 0.014%

    No Known Activations