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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to decision-making processes and choice

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.70
     below
    -0.59
     Below
    -0.54
    جيل
    -0.54
    iena
    -0.53
    plink
    -0.53
    чел
    -0.53
    fø
    -0.53
    pearl
    -0.53
    below
    -0.52
    POSITIVE LOGITS
    OGND
    0.61
    ThemeOverlay
    0.61
     ostavi
    0.59
    actionMode
    0.56
    RegressionTest
    0.56
    digarh
    0.56
    исленность
    0.54
     actionMode
    0.53
    Цитата
    0.52
    říklad
    0.51
    Act Density 0.063%

    No Known Activations