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

    Neuronpedia

    INDEX
    Explanations

    instances of events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "there have been" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arily
    -0.80
    arta
    -0.75
    poses
    -0.68
    culosis
    -0.66
     athlet
    -0.64
    would
    -0.63
    atra
    -0.62
    2019
    -0.62
    ribe
    -0.62
    entric
    -0.61
    POSITIVE LOGITS
     plenty
    0.93
    cffffcc
    0.79
     murm
    0.73
     lots
    0.71
     shown
    0.69
     several
    0.69
    FORE
    0.69
     tremendous
    0.68
    shown
    0.66
     countless
    0.66
    Act Density 0.033%

    No Known Activations