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

    Neuronpedia

    INDEX
    Explanations

    positions or locations within a space

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing position or location related to visual or spatial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.82
    eers
    -0.76
    fulness
    -0.73
    ARA
    -0.72
    fully
    -0.71
    é¾į
    -0.70
    abilities
    -0.67
    ALLY
    -0.67
     firsthand
    -0.65
    Wik
    -0.64
    POSITIVE LOGITS
     circle
    0.87
     spectrum
    0.84
     envelope
    0.83
     pyramid
    0.82
     globe
    0.80
     valley
    0.80
     continent
    0.78
     rectangle
    0.77
     country
    0.77
     equation
    0.76
    Act Density 0.160%

    No Known Activations