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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating quantities or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISSION
    -0.77
    EMENT
    -0.66
    autions
    -0.65
    ALE
    -0.65
     embr
    -0.64
    WARD
    -0.63
     stabilization
    -0.62
    ilic
    -0.62
    olitan
    -0.62
     antic
    -0.62
    POSITIVE LOGITS
     usual
    0.90
    average
    0.88
     average
    0.75
     others
    0.68
     Thousand
    0.66
     Sabha
    0.65
     anywhere
    0.64
    ptions
    0.64
    manac
    0.63
     whites
    0.63
    Act Density 0.120%

    No Known Activations