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

    Neuronpedia

    INDEX
    Explanations

    connections or relationships between entities

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0002
    -0.85
    é¾
    -0.67
    802
    -0.66
    402
    -0.66
     Pione
    -0.65
     DK
    -0.64
    Tour
    -0.62
    702
    -0.62
     Impossible
    -0.62
    Trend
    -0.61
    POSITIVE LOGITS
    worldly
    0.86
    selves
    0.82
    self
    0.76
    emonic
    0.75
     individually
    0.71
     merits
    0.71
    dayName
    0.69
    onductor
    0.68
    onymous
    0.68
    heric
    0.67
    Act Density 0.013%

    No Known Activations