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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alm
    -0.15
    jo
    -0.14
    íķĻêµIJ
    -0.13
    FormsModule
    -0.13
    wer
    -0.13
     dogs
    -0.13
    418
    -0.13
    itt
    -0.13
    ека
    -0.13
    RowAtIndexPath
    -0.13
    POSITIVE LOGITS
     paper
    0.33
     article
    0.33
    article
    0.26
    paper
    0.25
     Article
    0.24
    .paper
    0.23
    Paper
    0.23
     artikel
    0.22
    Article
    0.22
    -article
    0.21
    Act Density 0.036%

    No Known Activations