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

    Neuronpedia

    INDEX
    Explanations

    words related to changes, developments, and shifts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant changes or shifts in political and societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tickets
    -0.91
     Tickets
    -0.86
    iddles
    -0.81
     fared
    -0.76
    mates
    -0.74
    bugs
    -0.72
    parts
    -0.71
     tickets
    -0.71
    eworks
    -0.71
    kids
    -0.70
    POSITIVE LOGITS
     willingness
    1.58
     tendency
    1.55
     realization
    1.50
     resurgence
    1.44
     reliance
    1.43
     insistence
    1.43
     emergence
    1.41
     reluctance
    1.40
     unwillingness
    1.38
     emphasis
    1.34
    Act Density 0.394%

    No Known Activations