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

    Neuronpedia

    INDEX
    Explanations

    nouns and terms related to physical attributes or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mouths
    -0.16
    adox
    -0.15
    isex
    -0.15
    mania
    -0.15
    -neck
    -0.15
    mouth
    -0.14
    zych
    -0.14
    ãģĵãģĿ
    -0.13
    aucoup
    -0.13
    -mouth
    -0.13
    POSITIVE LOGITS
    nts
    0.16
    ÑĤÑİ
    0.15
    anium
    0.15
    ë¦
    0.14
    cket
    0.14
    ebra
    0.14
    pline
    0.14
    Markdown
    0.13
    culus
    0.13
    .getElements
    0.13
    Act Density 0.126%

    No Known Activations