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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.62
     can
    -0.90
     ***!
    -0.89
    ⓧ
    -0.89
     to
    -0.88
    /*
    -0.87
    HasColumnType
    -0.87
    <eos>
    -0.87
     in
    -0.85
     for
    -0.85
    POSITIVE LOGITS
     increa
    3.41
     ?...
    3.40
     fta
    3.39
     !...
    3.35
     wien
    3.34
     affor
    3.29
     emphat
    3.27
     effe
    3.23
     ftu
    3.17
     aen
    3.17
    Act Density 0.501%

    No Known Activations