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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "before" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "before"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DC
    -0.71
    catentry
    -0.69
    Hen
    -0.68
    Goal
    -0.67
    PROV
    -0.67
    Chel
    -0.66
    wire
    -0.66
    Herm
    -0.66
    CLASSIFIED
    -0.66
    Die
    -0.66
    POSITIVE LOGITS
     sunset
    0.82
     Thumbnails
    0.72
    swer
    0.72
     sunrise
    0.71
     midnight
    0.67
    vre
    0.65
     fading
    0.65
     supper
    0.64
    lihood
    0.63
    theless
    0.63
    Act Density 0.056%

    No Known Activations