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

    Neuronpedia

    INDEX
    Explanations

    references to final stages or conclusions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elta
    -0.15
     volt
    -0.14
    æł·çļĦ
    -0.14
    eselect
    -0.14
    offs
    -0.14
    rel
    -0.13
    jure
    -0.13
    onga
    -0.13
    edge
    -0.13
    kal
    -0.13
    POSITIVE LOGITS
    mente
    0.19
    zik
    0.17
    ised
    0.17
    arily
    0.16
    ament
    0.16
    ize
    0.15
    izing
    0.15
    YNAMIC
    0.14
    ising
    0.14
    eniable
    0.14
    Act Density 0.023%

    No Known Activations