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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "multiple"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "multiple"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.75
    Dialogue
    -0.73
    iquette
    -0.71
    nothing
    -0.71
    NER
    -0.69
    instead
    -0.68
    naire
    -0.67
    lua
    -0.67
    oop
    -0.65
    NEY
    -0.65
    POSITIVE LOGITS
     sclerosis
    1.75
    xes
    1.55
     iterations
    1.15
     layers
    1.14
     instances
    1.12
    ples
    1.11
     generations
    1.10
     versions
    1.09
     facets
    1.09
     occasions
    1.08
    Act Density 0.050%

    No Known Activations