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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something that continues to exist or persist

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating continuity or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.97
    DragonMagazine
    -0.70
    ongyang
    -0.67
    isson
    -0.67
    insula
    -0.66
    PsyNetMessage
    -0.66
    ellar
    -0.66
    onz
    -0.64
    rones
    -0.63
    ranch
    -0.62
    POSITIVE LOGITS
     unchanged
    1.18
     unanswered
    1.10
     intact
    1.08
     undefeated
    1.02
     unsolved
    1.02
     undecided
    1.00
     unaffected
    0.93
     steadfast
    0.93
     unbeaten
    0.92
     untouched
    0.90
    Act Density 0.033%

    No Known Activations