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

    Neuronpedia

    INDEX
    Explanations

    phrases related to striped patterns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stripes and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.74
     Rodham
    -0.68
    ibles
    -0.67
    20439
    -0.67
     Clockwork
    -0.66
     Cambodia
    -0.66
     Ing
    -0.66
    igham
    -0.65
    Ranked
    -0.65
     minimized
    -0.65
    POSITIVE LOGITS
     stripes
    3.11
     stripe
    2.64
    strip
    2.32
     Bend
    1.80
    stri
    1.73
     striped
    1.24
     allegiance
    0.98
     salute
    0.96
     Stri
    0.91
     bend
    0.90
    Act Density 0.019%

    No Known Activations