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

    Neuronpedia

    INDEX
    Explanations

    references to technology-related topics or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mijne
    -0.79
     affari
    -0.66
     contemporaine
    -0.65
     zijne
    -0.62
     zobac
    -0.61
     uwag
    -0.60
     étrangère
    -0.60
     realizacji
    -0.59
     robić
    -0.59
     duquel
    -0.59
    POSITIVE LOGITS
     du
    0.65
     au
    0.60
     d
    0.60
     aux
    0.56
     des
    0.51
     poussière
    0.49
     cheminée
    0.48
     à
    0.48
     riuscito
    0.46
     dans
    0.46
    Act Density 0.290%

    No Known Activations