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

    Neuronpedia

    INDEX
    Explanations

    descriptions indicating a level of quality or extent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fairly" indicating a moderate or measured tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STER
    -0.73
     Extensions
    -0.66
    inis
    -0.66
     Landing
    -0.66
     Tao
    -0.64
    ipper
    -0.64
    RY
    -0.63
    aer
    -0.62
     Plans
    -0.62
     Archives
    -0.61
    POSITIVE LOGITS
    itably
    0.98
     manageable
    0.86
     fair
    0.85
     fairly
    0.83
     accurate
    0.82
    ensical
    0.82
     readable
    0.79
     harmless
    0.78
    cipled
    0.77
     evenly
    0.77
    Act Density 0.004%

    No Known Activations