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

    Neuronpedia

    INDEX
    Explanations

    scientific observations and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to observations and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iery
    -0.73
    gm
    -0.71
    ordinate
    -0.69
    iencies
    -0.67
    enic
    -0.66
    avis
    -0.65
    events
    -0.63
    tiny
    -0.63
    estones
    -0.63
     saline
    -0.63
    POSITIVE LOGITS
    ally
    0.82
    naire
    0.79
    ary
    0.79
    eering
    0.75
    ariat
    0.74
     of
    0.71
    eers
    0.69
    hower
    0.69
    ptions
    0.66
    cember
    0.65
    Act Density 0.083%

    No Known Activations