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

    Neuronpedia

    INDEX
    Explanations

    terms related to precision and conditions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    tery
    -0.84
    Reviewer
    -0.82
    ged
    -0.78
    gers
    -0.77
    ting
    -0.74
    gered
    -0.68
    boards
    -0.67
    igate
    -0.67
    igans
    -0.66
     favourites
    -0.65
    POSITIVE LOGITS
    ursed
    1.20
    onduct
    1.19
    ursor
    1.14
    ognitive
    1.13
    orpor
    1.12
    entric
    1.10
    ounter
    1.09
    overed
    1.08
    urrent
    1.08
    ategory
    1.06
    Act Density 0.053%

    No Known Activations