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

    Neuronpedia

    INDEX
    Explanations

    references to betrayal and treachery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.18
     Friedman
    -0.15
    chematic
    -0.15
    -ли
    -0.15
    lei
    -0.14
     birim
    -0.14
    ribbon
    -0.14
    utz
    -0.14
    ockey
    -0.14
    ERN
    -0.13
    POSITIVE LOGITS
    ken
    0.17
    ãĥįãĥ«
    0.17
     upon
    0.16
     جز
    0.15
     alike
    0.15
    elp
    0.15
     pup
    0.14
     [[]
    0.14
     sweeping
    0.14
     Antar
    0.14
    Act Density 0.514%

    No Known Activations