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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the actions and behaviors of individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating political narratives and efforts regarding control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Else
    -0.68
     replies
    -0.65
    opy
    -0.64
     Pak
    -0.63
    ++
    -0.62
    @#&
    -0.61
     spoilers
    -0.60
     ISP
    -0.59
     Tsukuyomi
    -0.58
    DragonMagazine
    -0.57
    POSITIVE LOGITS
     championed
    1.09
     envisioned
    0.98
     pioneered
    0.91
     touted
    0.91
     promulg
    0.88
     inaug
    0.86
     perfected
    0.85
     abhor
    0.84
     outlined
    0.83
     sorely
    0.82
    Act Density 0.192%

    No Known Activations