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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and anecdotes mentioned in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     serons
    -0.57
    their
    -0.48
     recev
    -0.48
    Izvori
    -0.48
    Chham
    -0.47
     savons
    -0.46
     faisons
    -0.46
    MarshalTo
    -0.46
     متعلقه
    -0.45
    łgor
    -0.45
    POSITIVE LOGITS
     ourselves
    1.13
     apprehen
    0.99
     encomp
    0.95
     shenan
    0.95
     Souha
    0.92
     Messieurs
    0.91
     stickied
    0.88
     unspeak
    0.88
     intersper
    0.86
     disreg
    0.85
    Act Density 0.225%

    No Known Activations