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

    Neuronpedia

    INDEX
    Explanations

    keywords related to military, political, and social topics

    oai_token-act-pair · gpt-3.5-turbo

    references to social and political issues involving people and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lopp
    -0.73
    Cooldown
    -0.70
    asma
    -0.62
    tim
    -0.59
    DN
    -0.56
    PN
    -0.56
    olen
    -0.56
    yden
    -0.55
    Lat
    -0.55
    apego
    -0.54
    POSITIVE LOGITS
     onto
    0.86
     squarely
    0.83
     into
    0.83
     guiActiveUnfocused
    0.66
     shine
    0.65
     accountable
    0.65
     resonate
    0.64
     seriously
    0.60
     imaginable
    0.60
    into
    0.59
    Act Density 1.183%

    No Known Activations