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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate notable developments or milestones in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تانيه
    -0.53
     joaat
    -0.53
    enumii
    -0.52
    tahankan
    -0.49
    urent
    -0.48
    bibitem
    -0.47
    BagConstraints
    -0.47
     originais
    -0.46
     fidé
    -0.46
    hibe
    -0.45
    POSITIVE LOGITS
    finally
    0.83
     finally
    0.82
     FINALLY
    0.75
     endlich
    0.72
     finalmente
    0.70
     enfin
    0.69
     otomatig
    0.67
    ftagPool
    0.62
    :✨
    0.62
    FINALLY
    0.61
    Act Density 0.472%

    No Known Activations