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

    Neuronpedia

    INDEX
    Explanations

    references to imperialism and its related historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.17
    istan
    -0.15
    ãĥĨãĥ«
    -0.15
    wyn
    -0.15
    bjerg
    -0.15
    ãĥ©ãĥ³ãĥī
    -0.15
    erot
    -0.15
    365
    -0.14
    åĦ¿
    -0.14
    nett
    -0.14
    POSITIVE LOGITS
    wide
    0.20
    -wide
    0.19
    iyet
    0.15
    871
    0.14
    /Common
    0.14
    éĻħ
    0.14
    Wide
    0.14
    /Foundation
    0.14
    ulton
    0.13
    ople
    0.13
    Act Density 0.028%

    No Known Activations