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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "There was" appears followed by a description

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "there was" indicating the presence of information or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.69
    mare
    -0.63
    ®
    -0.62
     Experts
    -0.61
    owe
    -0.61
     Gleaming
    -0.59
    otic
    -0.59
    united
    -0.59
    allows
    -0.59
    Recommended
    -0.58
    POSITIVE LOGITS
     pandemonium
    0.89
    emonium
    0.82
     uproar
    0.81
     plenty
    0.74
     outcry
    0.74
     murm
    0.74
     applause
    0.73
     speculation
    0.69
     confusion
    0.68
    onnaissance
    0.67
    Act Density 0.080%

    No Known Activations