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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating waiting or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to contractual obligations and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allegedly
    -0.64
     propelled
    -0.58
     initially
    -0.56
     reportedly
    -0.56
     originally
    -0.54
     enters
    -0.53
     acceler
    -0.53
     Kaiser
    -0.53
     apprehended
    -0.53
     supposedly
    -0.53
    POSITIVE LOGITS
     ;)
    0.94
     ðŁĻĤ
    0.80
     sanity
    0.74
     :)
    0.74
     :-)
    0.74
     someday
    0.72
     anytime
    0.71
     myself
    0.69
     ðŁĺ
    0.67
     popcorn
    0.67
    Act Density 1.051%

    No Known Activations