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

    Neuronpedia

    INDEX
    Explanations

    times when something is different or unique from previous instances

    oai_token-act-pair · gpt-3.5-turbo

    references to changes or contrasts in situations over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olor
    -0.77
    -+-+
    -0.73
     Others
    -0.72
     Explan
    -0.69
    arine
    -0.67
    Alert
    -0.65
    lees
    -0.64
    ships
    -0.63
    ually
    -0.62
    Others
    -0.62
    POSITIVE LOGITS
     emphasis
    0.72
    instead
    0.68
     instead
    0.68
    phasis
    0.68
    quickShipAvailable
    0.68
     understatement
    0.67
     opted
    0.66
     lucky
    0.64
    pheus
    0.63
     distinction
    0.61
    Act Density 0.254%

    No Known Activations