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

    Neuronpedia

    INDEX
    Explanations

    proper names and names of places

    oai_token-act-pair · gpt-3.5-turbo

    various punctuation marks and transitions in textual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mund
    -0.75
    bow
    -0.66
    afety
    -0.62
     Woodward
    -0.61
    arah
    -0.61
    direction
    -0.60
    leen
    -0.60
     fundament
    -0.60
    gradient
    -0.58
    ãĤ§
    -0.58
    POSITIVE LOGITS
     respectively
    1.44
    anwhile
    0.78
    Interstitial
    0.77
    ibaba
    0.75
    avorite
    0.74
    aucuses
    0.73
     vying
    0.73
     among
    0.72
     latter
    0.72
     apiece
    0.71
    Act Density 0.498%

    No Known Activations