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

    Neuronpedia

    INDEX
    Explanations

    mentions of "Fox News" and related controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idd
    -0.17
     fault
    -0.17
    IDD
    -0.15
    ElementType
    -0.15
    uess
    -0.15
    viÄį
    -0.13
    raman
    -0.13
    ê°ģ
    -0.13
    ouv
    -0.13
    idor
    -0.13
    POSITIVE LOGITS
    umo
    0.15
    UILTIN
    0.14
    ANGO
    0.14
    ãĤ¤ãĥ«
    0.14
     mote
    0.14
    atology
    0.14
    ynes
    0.14
    å§Ķ
    0.14
     Marble
    0.14
    003
    0.13
    Act Density 0.015%

    No Known Activations