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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "more" signaling a comparative context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atan
    -0.81
    uca
    -0.73
    xtap
    -0.68
    uckle
    -0.68
    adium
    -0.64
    idated
    -0.62
    pton
    -0.61
    imaru
    -0.61
    abama
    -0.60
    ipment
    -0.60
    POSITIVE LOGITS
     importantly
    1.63
     than
    1.21
     ado
    0.93
     millenn
    0.89
     Than
    0.86
     interestingly
    0.84
     accurately
    0.81
     controvers
    0.79
     broadly
    0.78
     stringent
    0.78
    Act Density 0.122%

    No Known Activations