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

    Neuronpedia

    INDEX
    Explanations

    topics related to societal and ethical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ument
    -0.16
    ades
    -0.16
     elt
    -0.15
    end
    -0.15
     Bang
    -0.15
    allee
    -0.15
     Kar
    -0.14
     Adoption
    -0.14
     Carbon
    -0.14
    anch
    -0.14
    POSITIVE LOGITS
    ä½ľä¸º
    0.16
    utex
    0.16
    lund
    0.15
     input
    0.14
    ewater
    0.14
    ystone
    0.14
     INCLUDED
    0.14
    shine
    0.14
    ewood
    0.14
     Translator
    0.14
    Act Density 0.287%

    No Known Activations