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

    Neuronpedia

    INDEX
    Explanations

    technical jargon or keywords related to programming and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assin
    -0.17
    bole
    -0.15
     Dud
    -0.14
    /DTD
    -0.14
    gal
    -0.14
    IGH
    -0.14
    apers
    -0.14
    ÅĦst
    -0.14
     deb
    -0.14
    .templates
    -0.13
    POSITIVE LOGITS
    apult
    0.19
    ervlet
    0.15
     addCriterion
    0.15
    adiens
    0.15
    orthand
    0.15
    allen
    0.14
    á»ij
    0.14
    eum
    0.13
    Parms
    0.13
    ãĢģãģª
    0.13
    Act Density 0.011%

    No Known Activations