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

    Neuronpedia

    INDEX
    Explanations

    the word "out" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.84
    avorite
    -0.74
     resil
    -0.65
     tyr
    -0.65
     misunder
    -0.64
     expend
    -0.63
     grooming
    -0.63
    itational
    -0.62
    everal
    -0.61
     slightest
    -0.60
    POSITIVE LOGITS
    doors
    1.03
    door
    0.99
    lier
    0.95
    fitted
    0.92
    stretched
    0.90
    landish
    0.87
    dated
    0.87
    flow
    0.86
    skirts
    0.83
    casts
    0.82
    Act Density 0.033%

    No Known Activations