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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing specific aspects of something

    oai_token-act-pair · gpt-3.5-turbo

    references to different facets or attributes of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ander
    -0.82
    anders
    -0.72
    usable
    -0.72
    ettings
    -0.72
    hov
    -0.72
    andering
    -0.71
    ricanes
    -0.70
    annis
    -0.68
    gencies
    -0.68
    inflamm
    -0.62
    POSITIVE LOGITS
    SourceFile
    0.91
    uality
    0.86
     aspects
    0.82
    stones
    0.81
     facets
    0.80
    iveness
    0.76
    lihood
    0.74
    ality
    0.73
    stone
    0.73
    rait
    0.71
    Act Density 0.010%

    No Known Activations