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

    Neuronpedia

    INDEX
    Explanations

    technical details and figures

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )</
    -0.66
    ãĢį
    -0.62
    Untitled
    -0.60
    Life
    -0.57
     [âĢ¦]
    -0.57
    âĢ¦"
    -0.55
    </
    -0.52
    ooting
    -0.52
     mirac
    -0.51
     âĢ¦"
    -0.51
    POSITIVE LOGITS
     Scrib
    0.67
    lishes
    0.63
     Mulcair
    0.58
    ansky
    0.58
    dict
    0.58
     âĵĺ
    0.56
    evin
    0.55
     Frazier
    0.55
    doi
    0.55
     diction
    0.55
    Act Density 1.871%

    No Known Activations