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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ethene
    -0.71
    ethane
    -0.64
    toluene
    -0.56
    aniline
    -0.54
    acetate
    -0.52
    perus
    -0.52
     earnestness
    -0.51
    ltä
    -0.51
    lamino
    -0.50
    Iné
    -0.50
    POSITIVE LOGITS
     RY
    0.97
     DY
    0.97
     dovr
    0.95
     hy
    0.92
    hy
    0.90
    Hy
    0.90
     Hy
    0.90
     LY
    0.89
     Dy
    0.89
     HY
    0.88
    Act Density 0.279%

    No Known Activations