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

    Neuronpedia

    INDEX
    Explanations

    personal preferences, opinions, and visions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal thought and preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phelps
    -0.68
    Asset
    -0.63
     unveiling
    -0.61
    tml
    -0.60
    uctions
    -0.59
     moderator
    -0.59
     omission
    -0.58
    UGC
    -0.57
     Nanto
    -0.57
    âĸł
    -0.57
    POSITIVE LOGITS
     dreamed
    0.84
     normally
    0.83
     envisioned
    0.82
     traditionally
    0.82
     described
    0.80
     ordinarily
    0.80
     deems
    0.78
     perceive
    0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.72
     characterize
    0.71
    Act Density 0.300%

    No Known Activations