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

    Neuronpedia

    INDEX
    Explanations

    terms related to legitimacy and validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paces
    -0.48
     Dumont
    -0.47
    KommentareTeilen
    -0.46
     mena
    -0.44
    oxidase
    -0.44
     брать
    -0.44
     compressed
    -0.43
    toks
    -0.43
    umbra
    -0.43
    Occurred
    -0.42
    POSITIVE LOGITS
    AsUp
    0.86
    ReusableCell
    0.78
     stället
    0.72
     šaty
    0.69
     onAnimation
    0.67
    беріга
    0.67
     brancas
    0.67
     createState
    0.65
     ffilm
    0.65
     quæ
    0.65
    Act Density 0.769%

    No Known Activations