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

    Neuronpedia

    INDEX
    Explanations

    references to tarot cards and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stra
    -0.19
    ias
    -0.16
    sert
    -0.15
    ello
    -0.15
    elho
    -0.15
    ToFront
    -0.15
    eli
    -0.14
    ders
    -0.14
    ene
    -0.14
    sth
    -0.14
    POSITIVE LOGITS
     Tar
    0.30
    Tar
    0.27
     tar
    0.25
    iffs
    0.23
    tar
    0.20
    leton
    0.19
    heel
    0.18
    zan
    0.18
    زاÙĨ
    0.18
    _tar
    0.17
    Act Density 0.007%

    No Known Activations