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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I would say" and its variations expressing personal opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uras
    -0.71
    hs
    -0.69
     Written
    -0.65
    vas
    -0.65
    CW
    -0.64
    icz
    -0.63
    HOU
    -0.63
    emen
    -0.63
    onut
    -0.62
    eatured
    -0.62
    POSITIVE LOGITS
     goodbye
    0.89
     anecd
    0.73
     that
    0.71
     hello
    0.70
     è£ıè
    0.67
     congratulations
    0.67
     congr
    0.62
     95
    0.61
     Mub
    0.60
     yes
    0.60
    Act Density 0.093%

    No Known Activations