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

    Neuronpedia

    INDEX
    Explanations

    references to winners, winning, and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.17
    undi
    -0.16
    leck
    -0.15
    antar
    -0.15
    zi
    -0.15
    WD
    -0.15
    jang
    -0.15
    ers
    -0.14
    İ
    -0.14
    stry
    -0.14
    POSITIVE LOGITS
    icts
    0.17
    nable
    0.17
    NECT
    0.15
    ãĥ«ãĥī
    0.14
    oser
    0.14
    æĬķ注
    0.14
    atement
    0.14
    pha
    0.14
     Ment
    0.14
    ç·ł
    0.14
    Act Density 0.005%

    No Known Activations