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

    Neuronpedia

    INDEX
    Explanations

    phrases related to history and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assumptions or beliefs about past situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akens
    -0.72
    wake
    -0.69
     tonight
    -0.68
     Secondly
    -0.66
    today
    -0.66
     restores
    -0.65
     enhances
    -0.64
     shifts
    -0.62
     recent
    -0.62
     Yesterday
    -0.61
    POSITIVE LOGITS
    emed
    0.78
     feared
    0.76
     doubted
    0.75
     believed
    0.75
     thought
    0.73
     regarded
    0.72
     seemed
    0.72
     considered
    0.71
     suspected
    0.69
    kept
    0.68
    Act Density 0.461%

    No Known Activations