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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and references to data scales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icari
    -0.20
    ValueCollection
    -0.18
     endregion
    -0.17
    endregion
    -0.16
    middle
    -0.15
     دÙĪÙħ
    -0.15
    oyer
    -0.15
    ãĤĤãģĨ
    -0.15
    iii
    -0.14
    _second
    -0.14
    POSITIVE LOGITS
    1
    0.48
    01
    0.40
    001
    0.34
     first
    0.34
    Û±
    0.30
    ï¼ij
    0.28
    第ä¸Ģ
    0.28
     第ä¸Ģ
    0.27
     첫
    0.26
     First
    0.25
    Act Density 0.172%

    No Known Activations