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

    Neuronpedia

    INDEX
    Explanations

    language describing conditions, situations, or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "there was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.75
     ®
    -0.65
    opathic
    -0.64
    owe
    -0.62
     indo
    -0.62
    codes
    -0.61
     unemploy
    -0.61
    Recommended
    -0.59
     Gleaming
    -0.59
    ologies
    -0.59
    POSITIVE LOGITS
     uproar
    1.03
     murm
    0.96
     outcry
    0.92
     applause
    0.87
     whispers
    0.86
     pandemonium
    0.85
     hesitation
    0.84
     rumors
    0.83
     confusion
    0.82
     speculation
    0.82
    Act Density 0.135%

    No Known Activations