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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and references that indicate academic citations or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    że
    -0.17
    meni
    -0.16
    oa
    -0.15
    lož
    -0.15
    gnore
    -0.15
    _OT
    -0.15
    .lambda
    -0.14
    _MAXIMUM
    -0.14
    á»ij
    -0.14
    //{{
    -0.14
    POSITIVE LOGITS
    luk
    0.17
    oner
    0.17
    iar
    0.16
     Eins
    0.16
    REET
    0.15
     Pascal
    0.15
    ipt
    0.14
    ãĥĥãĤ¯ãĤ¹
    0.14
    ingles
    0.14
    -beta
    0.14
    Act Density 0.165%

    No Known Activations