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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a large amount or increase in activity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large amounts or surges of activity or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.82
    ©¶æ
    -0.71
    nect
    -0.64
    tarians
    -0.63
     Flags
    -0.63
    rongh
    -0.63
     Territory
    -0.63
    rib
    -0.62
     harmless
    -0.62
     Governors
    -0.61
    POSITIVE LOGITS
    tro
    0.89
    pour
    0.89
    azard
    0.76
    storm
    0.76
    DragonMagazine
    0.76
    channelAvailability
    0.74
    astic
    0.73
     barrage
    0.70
     tide
    0.70
     churn
    0.70
    Act Density 0.116%

    No Known Activations