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

    Neuronpedia

    INDEX
    Explanations

    references to wolves, particularly in various contexts or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agger
    -0.16
    abel
    -0.15
    nown
    -0.14
    ti
    -0.14
    KA
    -0.14
    verted
    -0.14
    ÄĻk
    -0.14
     Xen
    -0.13
     opport
    -0.13
    itate
    -0.13
    POSITIVE LOGITS
    heim
    0.21
    inkel
    0.15
    pawn
    0.15
     Redistributions
    0.15
    uÃŃ
    0.15
    обÑħодим
    0.15
    isode
    0.14
    ãĤ¢ãĤ¤
    0.14
    sonian
    0.14
    heimer
    0.14
    Act Density 0.010%

    No Known Activations