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

    Neuronpedia

    INDEX
    Explanations

    references to various group structures or hierarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.15
    iltr
    -0.15
    ray
    -0.15
    igua
    -0.15
     Vog
    -0.14
    upo
    -0.14
     dam
    -0.14
     Demp
    -0.14
    vore
    -0.14
    onders
    -0.14
    POSITIVE LOGITS
    ings
    0.18
    öt
    0.16
    /team
    0.16
    ENCHMARK
    0.15
    sWith
    0.15
    yn
    0.15
    .freeze
    0.15
    stant
    0.15
    atsby
    0.14
    sons
    0.14
    Act Density 0.030%

    No Known Activations