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

    Neuronpedia

    INDEX
    Explanations

    the word "humanity" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to humanity and its characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.69
     Gillespie
    -0.65
    urations
    -0.65
    raph
    -0.64
    abet
    -0.64
     FEC
    -0.63
    ockey
    -0.62
    ESH
    -0.61
    é¾įå
    -0.61
    RECT
    -0.60
    POSITIVE LOGITS
    ankind
    1.00
     beings
    0.90
    zee
    0.76
    arily
    0.76
    idis
    0.75
    ÃŃs
    0.73
     flourishing
    0.72
     inhab
    0.71
    itably
    0.71
    arium
    0.70
    Act Density 0.021%

    No Known Activations