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

    Neuronpedia

    INDEX
    Explanations

    terms related to knots or bundle-like structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to knots and buns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.87
    ×Ļ
    -0.72
    baugh
    -0.67
    rador
    -0.67
     obser
    -0.65
     administ
    -0.64
    arthed
    -0.64
    taboola
    -0.63
    д
    -0.63
    geist
    -0.62
    POSITIVE LOGITS
    ting
    1.08
    ches
    0.95
     knots
    0.93
     knot
    0.90
    weed
    0.87
    ty
    0.86
    hered
    0.85
    urtles
    0.82
    ishes
    0.82
    terness
    0.75
    Act Density 0.033%

    No Known Activations