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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forms
    -0.15
     forms
    -0.15
     noise
    -0.14
     Trevor
    -0.14
    onen
    -0.14
     enclosure
    -0.14
     Lynch
    -0.14
     smoke
    -0.14
     Hills
    -0.14
    noise
    -0.14
    POSITIVE LOGITS
    yor
    0.16
    jed
    0.16
    conj
    0.15
    ortex
    0.14
     Cah
    0.14
    ød
    0.14
    nim
    0.14
     ÑĤÑĢанÑģп
    0.14
    curacy
    0.13
    lád
    0.13
    Act Density 0.089%

    No Known Activations