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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing individual actions or objects

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases emphasizing the word "single."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bots
    -0.88
    ammers
    -0.81
    rils
    -0.80
    Rs
    -0.80
    olas
    -0.80
    eln
    -0.79
    iddles
    -0.76
    letters
    -0.76
    wings
    -0.76
    strings
    -0.75
    POSITIVE LOGITS
     imaginable
    1.18
     conceivable
    1.14
     facet
    1.05
    THING
    1.04
     person
    1.02
     thing
    1.01
     aspect
    0.97
     member
    0.94
     participant
    0.94
     ounce
    0.93
    Act Density 0.094%

    No Known Activations