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

    Neuronpedia

    INDEX
    Explanations

    questions and considerations related to alternatives and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.52
     jspb
    -0.49
    wiście
    -0.48
    StructEnd
    -0.44
    ритори
    -0.41
     Nearly
    -0.40
    zko
    -0.40
    뀐
    -0.40
    Stderr
    -0.39
    ่วง
    -0.39
    POSITIVE LOGITS
     other
    1.79
     elsewhere
    1.69
     autre
    1.62
    other
    1.52
     another
    1.45
     OTHER
    1.42
    別の
    1.41
     andere
    1.40
    autres
    1.38
    Other
    1.33
    Act Density 0.645%

    No Known Activations