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

    Neuronpedia

    INDEX
    Explanations

    sequences that describe movement or transition

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kona
    -0.60
     NTIS
    -0.56
     unspeak
    -0.56
     Middles
    -0.53
     ··
    -0.52
     unlaw
    -0.52
     censiti
    -0.52
     Bayard
    -0.51
     OGS
    -0.50
    mogat
    -0.49
    POSITIVE LOGITS
     originally
    0.92
     original
    0.73
    originally
    0.73
     earlier
    0.72
    original
    0.71
     orig
    0.70
    Originally
    0.70
    Original
    0.68
    ORIGINAL
    0.68
     originales
    0.66
    Act Density 0.418%

    No Known Activations