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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific measurements and results in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     really
    -0.54
    提
    -0.49
    тельству
    -0.49
     just
    -0.49
     very
    -0.48
     gener
    -0.48
     челове
    -0.48
     truly
    -0.47
     human
    -0.46
     x
    -0.46
    POSITIVE LOGITS
     مرئيه
    0.70
     Савезне
    0.70
     betweenstory
    0.67
    WebVitals
    0.67
    </tfoot>
    0.66
    %)$
    0.64
    reamble
    0.63
    Czytaj
    0.63
     ModelRenderer
    0.61
    anyahu
    0.60
    Act Density 2.335%

    No Known Activations