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

    Neuronpedia

    INDEX
    Explanations

    references to a central location or focus point

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "center"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atson
    -0.72
    etimes
    -0.69
    areth
    -0.68
    BIT
    -0.67
    apons
    -0.67
    pload
    -0.66
     Griffith
    -0.64
    THER
    -0.64
    iggins
    -0.63
     cig
    -0.63
    POSITIVE LOGITS
    pieces
    1.13
    tenance
    0.88
    point
    0.86
     centers
    0.84
     fielder
    0.81
    uve
    0.81
     center
    0.80
    points
    0.75
    bard
    0.75
    vier
    0.74
    Act Density 0.025%

    No Known Activations