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

    Neuronpedia

    INDEX
    Explanations

    words related to contributing or involvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contributions to various topics or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WIND
    -0.68
    hots
    -0.67
    HUD
    -0.66
    BuyableInstoreAndOnline
    -0.66
    CHAT
    -0.65
    mare
    -0.65
    DOWN
    -0.64
    STAT
    -0.64
    DragonMagazine
    -0.64
    TIT
    -0.64
    POSITIVE LOGITS
     compensate
    0.83
     counteract
    0.76
     fund
    0.75
     offset
    0.75
     behalf
    0.74
     accumulate
    0.73
     propagate
    0.73
     ensure
    0.72
     sustain
    0.72
     assist
    0.71
    Act Density 0.102%

    No Known Activations