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

    Neuronpedia

    INDEX
    Explanations

    code snippets and references to technical documentation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.04
    RTLR
    -0.61
     on
    -0.60
    .
    -0.60
    ,
    -0.58
     as
    -0.57
     s
    -0.57
     in
    -0.55
     consolidate
    -0.53
     at
    -0.53
    POSITIVE LOGITS
     keramik
    1.40
     alkoh
    1.39
     kram
    1.39
     antik
    1.35
     kosme
    1.34
     abnorm
    1.33
     silikon
    1.31
     robus
    1.30
     plak
    1.30
     konkre
    1.29
    Act Density 0.332%

    No Known Activations