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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.74
     soñ
    -0.73
     surla
    -0.70
     électroniques
    -0.69
     pérd
    -0.68
    ſelves
    -0.68
     moschino
    -0.66
     humaine
    -0.65
     näytte
    -0.65
    хьтан
    -0.64
    POSITIVE LOGITS
     also
    0.84
     make
    0.83
     start
    0.79
     have
    0.76
     be
    0.74
     
    0.71
     finally
    0.71
     then
    0.69
     useState
    0.68
     a
    0.67
    Act Density 0.422%

    No Known Activations