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

    Neuronpedia

    INDEX
    Explanations

    mentions of certainty or confirmation in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "certainly" and its emphasis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.81
    uese
    -0.78
    ulative
    -0.76
    lay
    -0.75
    gencies
    -0.70
    lins
    -0.69
    bucks
    -0.69
    agus
    -0.67
    OSH
    -0.65
    gur
    -0.63
    POSITIVE LOGITS
     qualifies
    0.77
     deserved
    0.77
     behaved
    0.76
     benefited
    0.73
     deline
    0.73
     appreci
    0.69
     distinguished
    0.69
     appreciated
    0.68
     Kraken
    0.66
     ought
    0.66
    Act Density 0.024%

    No Known Activations