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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to America

    oai_token-act-pair · gpt-3.5-turbo

    terms related to America and academia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caution
    -0.67
     Kub
    -0.67
     Cell
    -0.64
     Dwarf
    -0.63
    PAC
    -0.62
     Stall
    -0.62
     fertil
    -0.61
     contraception
    -0.61
    eering
    -0.60
     spiral
    -0.60
    POSITIVE LOGITS
    iences
    1.02
    icans
    1.01
    illac
    0.98
    ILA
    0.94
    ilar
    0.93
    illes
    0.92
    iances
    0.92
    ienced
    0.91
    ican
    0.91
    ibl
    0.89
    Act Density 0.087%

    No Known Activations