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

    Neuronpedia

    INDEX
    Explanations

    numerical figures expressing specific quantities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inelli
    -0.74
     majesty
    -0.67
    aimon
    -0.66
    outer
    -0.66
     Directorate
    -0.65
    inka
    -0.65
     toast
    -0.62
    rador
    -0.62
     appre
    -0.61
    INTON
    -0.60
    POSITIVE LOGITS
     of
    0.83
    enance
    0.72
    plates
    0.70
    mable
    0.69
    frames
    0.69
    uid
    0.68
    metry
    0.68
    dot
    0.66
    phal
    0.66
     occurrences
    0.65
    Act Density 0.043%

    No Known Activations