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

    Neuronpedia

    INDEX
    Explanations

    mentions of distance or comparison in terms of extent or degree

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fold
    -0.68
     Benefits
    -0.66
    lez
    -0.66
    borough
    -0.65
    chio
    -0.64
    vation
    -0.63
     Cosponsors
    -0.62
     folds
    -0.61
     EntityItem
    -0.61
    Micro
    -0.61
    POSITIVE LOGITS
     indications
    0.74
     anyway
    0.73
     hasn
    0.72
     haven
    0.70
     unanswered
    0.69
     unexpl
    0.69
     only
    0.68
     provisional
    0.67
     unsuccessful
    0.66
     undisclosed
    0.65
    Act Density 0.972%

    No Known Activations