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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and terms related to restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.18
    åĨµ
    -0.16
    iling
    -0.15
    uz
    -0.15
    ver
    -0.14
    MP
    -0.14
     Either
    -0.14
     either
    -0.14
    mp
    -0.14
     EITHER
    -0.14
    POSITIVE LOGITS
     necessarily
    0.20
     yet
    0.19
     actual
    0.18
     mere
    0.17
    arkan
    0.16
     anymore
    0.15
     tuy
    0.15
     actually
    0.15
    jj
    0.14
    qi
    0.14
    Act Density 0.146%

    No Known Activations