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

    Neuronpedia

    INDEX
    Explanations

    references to social and political issues involving marginalized or underrepresented groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijd
    -0.14
    Rendering
    -0.14
    ãģĨãģ¡
    -0.14
     something
    -0.13
     Including
    -0.13
    ürn
    -0.13
     anything
    -0.13
    idlo
    -0.13
    Including
    -0.13
    iyel
    -0.13
    POSITIVE LOGITS
    's
    0.34
     being
    0.29
     vs
    0.28
     versus
    0.26
     finally
    0.24
     possibly
    0.23
    ’s
    0.23
    being
    0.23
     becoming
    0.22
     suddenly
    0.22
    Act Density 0.175%

    No Known Activations