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

    Neuronpedia

    INDEX
    Explanations

    details related to personal experiences and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    imon
    -0.63
     Occupations
    -0.58
    )"
    -0.58
     However
    -0.57
    lees
    -0.56
    olson
    -0.55
    )/
    -0.53
    ulative
    -0.51
    plin
    -0.51
     Alternatively
    -0.51
    POSITIVE LOGITS
     unexpectedly
    0.75
     shockingly
    0.74
    etheless
    0.70
     inexpl
    0.69
     mirac
    0.67
     mysteriously
    0.67
     boldly
    0.65
     Canaver
    0.64
     goddamn
    0.61
     finally
    0.60
    Act Density 1.298%

    No Known Activations