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

    Neuronpedia

    INDEX
    Explanations

    academic references and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofile
    -0.15
    ko
    -0.15
    uien
    -0.15
    tz
    -0.15
     muzzle
    -0.14
    ovie
    -0.14
    .Logf
    -0.14
    erral
    -0.14
     culo
    -0.14
    /files
    -0.14
    POSITIVE LOGITS
    statt
    0.17
    608
    0.16
     Cum
    0.15
    fold
    0.15
    458
    0.14
     inspir
    0.14
    Cum
    0.13
    ession
    0.13
     laps
    0.13
     Research
    0.13
    Act Density 0.287%

    No Known Activations