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

    Neuronpedia

    INDEX
    Explanations

    text that indicates emotional reactions or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raud
    -0.15
     itself
    -0.15
    .FindAsync
    -0.14
    zcze
    -0.14
     sigu
    -0.14
    etri
    -0.14
     doing
    -0.13
    otu
    -0.13
    äter
    -0.13
     Cos
    -0.13
    POSITIVE LOGITS
     even
    0.26
    even
    0.23
     Even
    0.20
    _even
    0.20
    Even
    0.20
     EVEN
    0.19
     despite
    0.18
     даже
    0.17
     whenever
    0.17
    ddit
    0.16
    Act Density 0.031%

    No Known Activations