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

    Neuronpedia

    INDEX
    Explanations

    phrases related to using something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the usage or function of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukemia
    -0.82
    76561
    -0.73
     Niet
    -0.73
    lees
    -0.68
    ModLoader
    -0.65
    EStream
    -0.65
    yright
    -0.65
    errors
    -0.64
     Rebell
    -0.64
     Cree
    -0.64
    POSITIVE LOGITS
     leverage
    1.00
     shorthand
    0.93
     pretext
    0.89
     bait
    0.85
     excuse
    0.85
     proxy
    0.84
     fodder
    0.83
     blackmail
    0.82
     guide
    0.79
     efficiently
    0.78
    Act Density 0.103%

    No Known Activations