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

    Neuronpedia

    INDEX
    Explanations

    parenthetical references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.54
     poignée
    -0.51
     poitrine
    -0.49
     leçon
    -0.48
     réputation
    -0.48
     licorne
    -0.47
     rédaction
    -0.47
     cathédrale
    -0.47
     laiton
    -0.46
     autocollant
    -0.46
    POSITIVE LOGITS
     Magee
    0.83
     PACE
    0.82
    ice
    0.78
    DCE
    0.76
    PACE
    0.73
     Bale
    0.73
     Cline
    0.72
     PSE
    0.72
     ICE
    0.72
     Pace
    0.72
    Act Density 0.404%

    No Known Activations