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

    Neuronpedia

    INDEX
    Explanations

    warning messages regarding graphic content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -1.05
     snoopy
    -0.95
     apprehen
    -0.93
     maneu
    -0.89
     milf
    -0.88
     ineffec
    -0.87
     kasa
    -0.84
     attemp
    -0.84
     mischie
    -0.84
     vagu
    -0.83
    POSITIVE LOGITS
     graphic
    0.59
     horror
    0.58
     gruesome
    0.56
     gross
    0.54
     trauma
    0.54
     traumatic
    0.52
    腥
    0.51
     horrific
    0.50
     shock
    0.49
     cada
    0.49
    Act Density 0.730%

    No Known Activations