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

    Neuronpedia

    INDEX
    Explanations

    dimensions and measurements

    oai_token-act-pair · gpt-3.5-turbo

    dimensions and sizes of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YN
    -0.88
    tag
    -0.74
    fed
    -0.73
    effects
    -0.70
    Cash
    -0.70
    Tea
    -0.68
    edu
    -0.67
    feed
    -0.66
    cash
    -0.66
    given
    -0.66
    POSITIVE LOGITS
     diameter
    1.03
    iameter
    0.83
     tradem
    0.76
     horizontally
    0.74
     circumference
    0.74
     radius
    0.73
    izont
    0.72
     apiece
    0.71
    izontal
    0.71
     hex
    0.70
    Act Density 0.075%

    No Known Activations