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

    Neuronpedia

    INDEX
    Explanations

    references to a particular point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing hypothetical scenarios or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onto
    -0.65
    ores
    -0.65
    itiz
    -0.61
    ourge
    -0.60
     itch
    -0.59
    onite
    -0.59
     promot
    -0.58
    inse
    -0.57
     ducks
    -0.57
     label
    -0.56
    POSITIVE LOGITS
     nutshell
    1.09
     meantime
    1.05
     context
    0.97
     case
    0.97
     cases
    0.94
     guise
    0.92
     vein
    0.89
     midst
    0.84
     respects
    0.84
     absence
    0.83
    Act Density 0.206%

    No Known Activations