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

    Neuronpedia

    INDEX
    Explanations

    instances where certainty or doubt is expressed about a particular piece of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "for" indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.56
    ashtra
    -0.56
    orbit
    -0.53
    portation
    -0.51
    operated
    -0.50
    Bloomberg
    -0.49
    http
    -0.49
     Dangerous
    -0.48
    venants
    -0.48
    taboola
    -0.48
    POSITIVE LOGITS
     sure
    1.00
     yourselves
    0.96
     yourself
    0.93
    bidden
    0.93
     example
    0.91
     awhile
    0.91
     instance
    0.90
    aging
    0.87
    gettable
    0.86
     ourselves
    0.86
    Act Density 0.164%

    No Known Activations