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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the word "than" to indicate exceeding or comparison

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that involve the word "than."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilic
    -0.73
     Juda
    -0.69
    uty
    -0.67
     Canaveral
    -0.66
    igible
    -0.66
     largeDownload
    -0.65
     ra
    -0.64
    etic
    -0.62
    esian
    -0.60
    opian
    -0.60
    POSITIVE LOGITS
     usual
    0.80
     ever
    0.71
    etheless
    0.71
    whel
    0.68
    average
    0.68
     others
    0.67
    vol
    0.66
    whelming
    0.65
     anything
    0.65
    catch
    0.63
    Act Density 0.102%

    No Known Activations