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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ours
    -0.15
     kys
    -0.14
    urs
    -0.13
     surre
    -0.13
    opro
    -0.13
     unge
    -0.13
    udios
    -0.13
    721
    -0.13
    own
    -0.13
    .alloc
    -0.13
    POSITIVE LOGITS
     Nature
    0.32
     paper
    0.30
     published
    0.28
     peer
    0.27
     journal
    0.27
    Nature
    0.26
     papers
    0.26
     publish
    0.25
     publishing
    0.25
    paper
    0.23
    Act Density 0.060%

    No Known Activations