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

    Neuronpedia

    INDEX
    Explanations

    references to acknowledgment in discussions of conflict or polarizing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.16
     Bundy
    -0.15
    -ser
    -0.15
    /MPL
    -0.15
    :^
    -0.14
    arest
    -0.14
    Ñĺ
    -0.13
    -Sah
    -0.13
    788
    -0.13
    unkt
    -0.13
    POSITIVE LOGITS
     Pu
    0.17
    OE
    0.16
    orean
    0.15
    rech
    0.14
    uet
    0.14
     Gro
    0.14
     uchar
    0.14
    rush
    0.14
    neau
    0.14
    lesia
    0.14
    Act Density 0.015%

    No Known Activations