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

    Neuronpedia

    INDEX
    Explanations

    word "all."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.61
     Caption
    -0.60
    itent
    -0.59
    geons
    -0.59
    ritis
    -0.56
    anwhile
    -0.56
    esis
    -0.55
    gee
    -0.55
    rained
    -0.54
    chard
    -0.54
    POSITIVE LOGITS
     sorts
    1.28
     kinds
    1.24
    ocating
    1.23
     manner
    1.14
     facets
    1.06
     aspects
    1.05
    usions
    1.00
    ocative
    0.92
    uding
    0.88
    ocations
    0.88
    Act Density 0.090%

    No Known Activations