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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating or beginning something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to beginnings or starting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mates
    -0.67
     prizes
    -0.66
    é¾įå
    -0.66
    é¾į
    -0.65
     ENTER
    -0.64
    osponsors
    -0.63
     inputs
    -0.61
     Amit
    -0.59
    ount
    -0.59
     rooft
    -0.59
    POSITIVE LOGITS
     anew
    1.19
     countdown
    1.07
     journey
    0.97
     fray
    0.89
    ourney
    0.88
     dialogue
    0.87
     discussion
    0.82
     conversation
    0.82
     process
    0.81
     semester
    0.80
    Act Density 0.128%

    No Known Activations