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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and relative clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ational
    -0.16
     bla
    -0.15
    erton
    -0.14
    rof
    -0.14
     Kis
    -0.14
     use
    -0.14
    amble
    -0.14
    Moon
    -0.14
     sponge
    -0.14
     ba
    -0.14
    POSITIVE LOGITS
     Verde
    0.15
    egin
    0.15
    isms
    0.14
    离
    0.14
    arez
    0.14
     ì¤Ģ
    0.14
    atik
    0.14
    779
    0.14
    __;
    0.14
    mans
    0.14
    Act Density 0.062%

    No Known Activations