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

    Neuronpedia

    INDEX
    Explanations

    references to comparative terms indicating context or sequences in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.66
    rington
    -0.64
     Gle
    -0.52
     toque
    -0.49
    askan
    -0.49
     demás
    -0.49
     Parkway
    -0.48
     clean
    -0.47
     tidur
    -0.47
     silencio
    -0.46
    POSITIVE LOGITS
     Latter
    1.35
     latter
    1.18
    后者
    1.14
    OGND
    1.09
     NSCoder
    1.08
    IndentedString
    1.04
     ProtoMessage
    1.03
    tonode
    1.01
    latter
    1.01
    1.01
    Act Density 0.102%

    No Known Activations