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

    Neuronpedia

    INDEX
    Explanations

    descriptions of research methodologies and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldt
    -0.16
    zet
    -0.16
    _DECLARE
    -0.15
    ugins
    -0.15
    ienda
    -0.15
    Īĺ
    -0.15
    holm
    -0.15
    ÑĮе
    -0.14
    udit
    -0.14
    otta
    -0.14
    POSITIVE LOGITS
    opoulos
    0.15
    ãĥ¬ãĥ¼
    0.15
     Corner
    0.15
     corner
    0.14
    .nb
    0.14
    corner
    0.14
     Craft
    0.14
    ran
    0.14
    aday
    0.14
    ddy
    0.13
    Act Density 0.200%

    No Known Activations