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

    Neuronpedia

    INDEX
    Explanations

    references to matrices and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISTA
    -0.15
    ά
    -0.14
    zag
    -0.14
     ë¶Ģíĥģ
    -0.14
    loom
    -0.14
    orges
    -0.14
    usta
    -0.14
    orado
    -0.14
    éĽĻ
    -0.13
    tul
    -0.13
    POSITIVE LOGITS
    asic
    0.16
    oya
    0.15
    çľ¼
    0.15
    .Apis
    0.14
    æ¯
    0.14
    ematik
    0.14
    象
    0.14
    ele
    0.14
     undisclosed
    0.14
    elen
    0.14
    Act Density 0.005%

    No Known Activations