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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating high agreement or significant proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportions or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.87
     compr
    -0.60
     Shad
    -0.57
     Reconstruction
    -0.55
     McAuliffe
    -0.55
     Trailer
    -0.54
    ADRA
    -0.53
     redes
    -0.53
     arsen
    -0.53
     Nadu
    -0.52
    POSITIVE LOGITS
     of
    1.12
    of
    0.97
    ta
    0.96
    Of
    0.93
    paced
    0.86
    fitted
    0.86
    stri
    0.84
    ranked
    0.84
     Of
    0.81
    scoring
    0.81
    Act Density 0.032%

    No Known Activations