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

    Neuronpedia

    INDEX
    Explanations

    references to the central or middle position

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific position or area in a field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.75
    soDeliveryDate
    -0.71
    ield
    -0.71
    IGHTS
    -0.70
    ãĥīãĥ©
    -0.68
    à¥
    -0.68
    ggies
    -0.65
    SIGN
    -0.64
    areth
    -0.63
    ished
    -0.63
    POSITIVE LOGITS
    pieces
    1.25
     fielder
    0.98
    piece
    0.85
    stadt
    0.84
    uve
    0.83
    lets
    0.79
    tenance
    0.79
    point
    0.77
    maid
    0.77
    mast
    0.76
    Act Density 0.028%

    No Known Activations