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

    Neuronpedia

    INDEX
    Explanations

    the word "purple" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Puritan" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning syllable "Pur"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    enegger
    -0.88
    worthiness
    -0.82
    ORGE
    -0.75
    schild
    -0.71
     removable
    -0.67
    holding
    -0.67
    external
    -0.67
    FAULT
    -0.66
    backed
    -0.63
    ORED
    -0.63
    POSITIVE LOGITS
    POSE
    0.87
    kie
    0.83
    zn
    0.82
    poses
    0.81
    pose
    0.80
    agin
    0.80
    rette
    0.80
    ryn
    0.79
    neys
    0.79
    itans
    0.78
    Act Density 0.011%

    No Known Activations