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

    Neuronpedia

    INDEX
    Explanations

    phrases related to overlapping entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to overlap and interconnectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Planet
    -0.75
    ibur
    -0.73
    acco
    -0.73
    igers
    -0.70
    olt
    -0.69
    ft
    -0.67
    ĸ
    -0.64
    gary
    -0.64
    HD
    -0.63
    rollers
    -0.62
    POSITIVE LOGITS
     overlapping
    1.25
     overlap
    1.22
     duplication
    0.86
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.84
     gaps
    0.84
    yip
    0.81
     synerg
    0.77
    ersed
    0.77
     intersections
    0.72
    entimes
    0.71
    Act Density 0.013%

    No Known Activations