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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start and end of events

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that indicate relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unaccount
    -0.64
    mbuds
    -0.63
    ukong
    -0.63
    cedented
    -0.61
    lihood
    -0.61
    dylib
    -0.59
    saf
    -0.58
    acus
    -0.58
    utch
    -0.58
    tumblr
    -0.58
    POSITIVE LOGITS
     gradually
    1.51
     progressively
    1.27
     progressing
    1.18
     thereafter
    1.18
     progressed
    1.16
     progresses
    1.15
     then
    1.11
     escal
    1.10
     escalate
    1.09
     culminating
    1.06
    Act Density 0.554%

    No Known Activations