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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of organizations or locations within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to research institutions and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    ãĥĥãĥī
    -0.63
    rities
    -0.60
    aez
    -0.58
    uphem
    -0.55
    URA
    -0.55
    EMBER
    -0.55
    biology
    -0.54
    ISA
    -0.54
    ibrary
    -0.53
    POSITIVE LOGITS
    itiveness
    0.65
    finding
    0.56
    bane
    0.54
     [*]
    0.52
    tip
    0.51
    zik
    0.50
    puff
    0.49
    herer
    0.48
    inning
    0.48
     tails
    0.48
    Act Density 1.065%

    No Known Activations