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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax terms and related concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.80
    bda
    -0.66
     shack
    -0.65
    EStream
    -0.64
     orally
    -0.63
     Ambro
    -0.59
     Thomson
    -0.59
     collecting
    -0.59
     Jem
    -0.58
     visually
    -0.57
    POSITIVE LOGITS
    ¬
    1.38
    į
    1.24
    Ĵ
    1.22
    ĸ
    1.18
    ħ
    1.18
    Ķ
    1.18
    ¤
    1.17
    ¡
    1.16
    º
    1.16
    ·
    1.15
    Act Density 0.157%

    No Known Activations