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

    Neuronpedia

    INDEX
    Explanations

    events or periods of time

    oai_token-act-pair · gpt-3.5-turbo

    historical events and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUND
    -0.61
    cause
    -0.61
    $.
    -0.61
    NOW
    -0.60
    ":"/
    -0.60
    soType
    -0.58
     rightful
    -0.58
     endif
    -0.58
    rather
    -0.55
    },"
    -0.54
    POSITIVE LOGITS
     there
    0.92
     we
    0.83
     they
    0.79
    ,
    0.70
    there
    0.70
     he
    0.69
     she
    0.66
     it
    0.64
     nobody
    0.58
     you
    0.57
    Act Density 0.499%

    No Known Activations