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

    Neuronpedia

    INDEX
    Explanations

    patterns related to dominance and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vap
    -0.16
    ften
    -0.16
     Ans
    -0.15
    ayan
    -0.15
    Ans
    -0.14
    oyer
    -0.14
    Encode
    -0.14
    éijij
    -0.14
    лика
    -0.14
     tro
    -0.13
    POSITIVE LOGITS
    kan
    0.16
    inkel
    0.15
    kening
    0.14
    urring
    0.14
    enen
    0.14
     Howe
    0.14
     imread
    0.14
    ecast
    0.14
    ahlen
    0.14
    ulong
    0.14
    Act Density 0.092%

    No Known Activations