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

    Neuronpedia

    INDEX
    Explanations

    references to nature or natural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oup
    -0.18
    hyper
    -0.16
    upe
    -0.15
    elts
    -0.15
    iw
    -0.15
    otti
    -0.14
    prech
    -0.14
    elt
    -0.14
    aire
    -0.14
    ics
    -0.13
    POSITIVE LOGITS
    URAL
    0.26
    aniel
    0.25
    asha
    0.23
     Nat
    0.22
    ürlich
    0.22
     nat
    0.21
    ural
    0.19
    anson
    0.19
    Nat
    0.19
    sume
    0.19
    Act Density 0.010%

    No Known Activations