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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific entities or names

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Fulham" and related anthrax contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.83
    ãĤ´ãĥ³
    -0.79
     Nightmares
    -0.76
     guiActiveUnfocused
    -0.72
     Mahar
    -0.70
    ++++++++
    -0.70
    ised
    -0.68
     Spa
    -0.68
    ****************
    -0.67
    ãģ®éŃĶ
    -0.66
    POSITIVE LOGITS
    bright
    0.90
    rase
    0.86
    ascript
    0.83
    inx
    0.78
    minded
    0.78
    mination
    0.75
    ongyang
    0.73
    lect
    0.73
    thora
    0.72
    rates
    0.71
    Act Density 0.118%

    No Known Activations