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

    Neuronpedia

    INDEX
    Explanations

    Russian or Slavic characters and words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "Ð" in varied contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.84
    iless
    -0.75
    ifully
    -0.73
    ifact
    -0.72
    ainer
    -0.71
    iewicz
    -0.70
    emort
    -0.69
    Boss
    -0.67
    enaries
    -0.66
     logger
    -0.65
    POSITIVE LOGITS
    ×IJ
    0.92
    0.84
    ¾
    0.82
    vez
    0.81
    ر
    0.81
    ´
    0.78
    ãĤī
    0.76
    IJ
    0.75
    ·
    0.75
    eland
    0.74
    Act Density 0.013%

    No Known Activations