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

    Neuronpedia

    INDEX
    Explanations

    phrases describing a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    references to specific points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brim
    -0.74
     poisons
    -0.73
    seless
    -0.68
    onym
    -0.66
    RED
    -0.65
     floats
    -0.64
    wine
    -0.64
    eton
    -0.64
     tricks
    -0.63
    onyms
    -0.63
    POSITIVE LOGITS
     adolescence
    0.95
    uberty
    0.93
     gestation
    0.92
     history
    0.90
     adulthood
    0.84
     infancy
    0.77
     succession
    0.77
     relation
    0.76
     pregnancy
    0.76
    history
    0.76
    Act Density 0.115%

    No Known Activations