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

    Neuronpedia

    INDEX
    Explanations

    variables and parameters related to dimensions and counts in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pity
    -0.61
     shame
    -0.57
    pity
    -0.51
    shame
    -0.49
    principalColumn
    -0.48
     Pity
    -0.48
    Shame
    -0.48
    afficheront
    -0.47
     insuffisamment
    -0.46
     Shame
    -0.45
    POSITIVE LOGITS
     +=
    0.90
     -=
    0.63
    +=
    0.60
    ]+=
    0.57
     .=
    0.50
     /=
    0.50
     *=
    0.47
     |=
    0.47
     &=
    0.47
    ///</
    0.46
    Act Density 0.182%

    No Known Activations