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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding adverbs of surprise

    np_acts-logits-general · gemini-2.0-flash

    perhaps surprisingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.73
    AndEndTag
    -0.61
    ngdoc
    -0.59
     esternos
    -0.59
     onOptions
    -0.59
    tableFuture
    -0.59
    íncia
    -0.58
    قایناق‌لار
    -0.58
     متعلقه
    -0.58
    ElementException
    -0.58
    POSITIVE LOGITS
     surprisingly
    1.98
     unsur
    1.72
     surprising
    1.71
     surprise
    1.65
     oddly
    1.59
     strangely
    1.58
    Surprisingly
    1.56
     Surprisingly
    1.55
    surprise
    1.50
     interestingly
    1.48
    Act Density 0.427%

    No Known Activations