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

    Neuronpedia

    INDEX
    Explanations

    locations or areas within a physical space, specifically corners

    oai_token-act-pair · gpt-3.5-turbo

    references to physical corners or metaphorical "corners" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inv
    -0.66
    ILA
    -0.65
     Schwarzenegger
    -0.64
    ELS
    -0.64
    apo
    -0.63
    umes
    -0.62
    ibus
    -0.61
    Exp
    -0.60
    ISA
    -0.60
    xp
    -0.59
    POSITIVE LOGITS
     corner
    3.97
     corners
    2.86
     Corner
    2.14
     edge
    1.29
     cornerback
    1.13
     bend
    1.10
     intersection
    1.10
     periphery
    1.04
     edges
    1.03
     alley
    1.01
    Act Density 0.012%

    No Known Activations