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

    Neuronpedia

    INDEX
    Explanations

    references to biological concepts or distinctions between biological entities

    oai_token-act-pair · gpt-3.5-turbo

    references to biological concepts and classifications related to gender

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.84
    naire
    -0.82
    esty
    -0.77
    eeper
    -0.77
    eca
    -0.71
    ebook
    -0.70
    rising
    -0.69
    adra
    -0.69
    essee
    -0.67
    urat
    -0.65
    POSITIVE LOGITS
     plaus
    1.05
     sciences
    0.95
     biologist
    0.89
     biologists
    0.87
     anthropology
    0.84
     biology
    0.83
     immortality
    0.82
     organisms
    0.80
     organism
    0.80
     evolution
    0.80
    Act Density 0.021%

    No Known Activations