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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions happening in front of an audience or observers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of a specific context or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aren
    -0.80
    dayName
    -0.78
     Cosponsors
    -0.77
    wcs
    -0.75
    QL
    -0.74
    >[
    -0.71
    lost
    -0.68
    Clar
    -0.67
    PDATE
    -0.65
    acci
    -0.64
    POSITIVE LOGITS
    rium
    0.73
    sight
    0.70
    agons
    0.70
     doors
    0.69
    thouse
    0.68
     scrimmage
    0.68
     Fury
    0.66
     doorstep
    0.65
     Hogwarts
    0.65
     VICE
    0.63
    Act Density 0.034%

    No Known Activations