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

    Neuronpedia

    INDEX
    Explanations

    words related to chronological or logical order

    oai_token-act-pair · gpt-3.5-turbo

    words related to predictions and forecasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.83
    witch
    -0.75
    Hub
    -0.69
    fax
    -0.67
    ikan
    -0.67
    ¯¯¯¯¯¯¯¯
    -0.66
    oshenko
    -0.66
    Helper
    -0.65
    ishi
    -0.64
    Sold
    -0.64
    POSITIVE LOGITS
     checkpoints
    0.74
    ential
    0.68
     fatal
    0.68
    iously
    0.67
     gestation
    0.67
     deaths
    0.67
     preced
    0.66
    SHIP
    0.63
     MGM
    0.62
    days
    0.62
    Act Density 0.052%

    No Known Activations