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

    Neuronpedia

    INDEX
    Explanations

    keywords related to current events or news

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    urated
    -0.76
    osponsors
    -0.68
    oru
    -0.67
    usters
    -0.65
    amia
    -0.65
    gur
    -0.64
    ardy
    -0.63
    anmar
    -0.61
    mented
    -0.60
    gotten
    -0.59
    POSITIVE LOGITS
     sucks
    0.74
     else
    0.71
     thereafter
    0.69
     though
    0.69
     depends
    0.68
     suffice
    0.67
    >>>>
    0.66
    soever
    0.65
     imaginable
    0.64
    event
    0.63
    Act Density 0.026%

    No Known Activations