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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events that have taken place

    oai_token-act-pair · gpt-3.5-turbo

    actions that indicate significant events or processes that have occurred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yond
    -0.69
    odic
    -0.66
    ennett
    -0.66
    Pak
    -0.65
    ighter
    -0.63
    incerity
    -0.63
    hart
    -0.62
    maxwell
    -0.61
    omorph
    -0.61
    thur
    -0.61
    POSITIVE LOGITS
     last
    0.87
     yesterday
    0.86
     earlier
    0.80
     originally
    0.78
     previously
    0.76
     unsuccessfully
    0.76
     Saddam
    0.74
     Doodle
    0.73
     Yanuk
    0.72
     unanimously
    0.69
    Act Density 0.284%

    No Known Activations