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

    Neuronpedia

    INDEX
    Explanations

    words related to stability and consistency

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of consistency or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.81
    aucus
    -0.76
    dor
    -0.75
    zan
    -0.69
    dylib
    -0.68
    artments
    -0.67
    LCS
    -0.67
    emis
    -0.67
    rero
    -0.67
    Sov
    -0.66
    POSITIVE LOGITS
     stream
    1.07
    motion
    0.94
     flow
    0.90
     drip
    0.89
     steady
    0.89
     pace
    0.84
     trickle
    0.80
     slope
    0.80
     progression
    0.79
     pulse
    0.78
    Act Density 0.037%

    No Known Activations