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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize a significant increase or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant amounts or extremes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wal
    -0.69
    gans
    -0.68
    alg
    -0.67
    Catal
    -0.66
    aris
    -0.65
    ene
    -0.65
    umes
    -0.64
     Georg
    -0.64
     Ideas
    -0.64
    etics
    -0.63
    POSITIVE LOGITS
     notch
    4.11
     peg
    1.38
     snag
    1.26
     tad
    1.14
     knot
    1.13
     latch
    1.06
     groove
    1.05
     downgrade
    1.04
     curv
    0.97
     slot
    0.96
    Act Density 0.025%

    No Known Activations