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

    Neuronpedia

    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -0.93
     overcrow
    -0.85
     apprehen
    -0.82
     impelled
    -0.78
     cushi
    -0.77
     disagre
    -0.77
     ineffec
    -0.76
     withal
    -0.74
     horrend
    -0.73
     endeavoured
    -0.73
    POSITIVE LOGITS
     espé
    1.30
     rè
    1.29
     meras
    1.25
     alkoh
    1.24
     anse
    1.22
     kosme
    1.22
     dì
    1.18
     utop
    1.18
     dè
    1.17
     kön
    1.16
    Act Density 0.158%

    No Known Activations