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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making and choices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.91
    ecake
    -0.79
    ocumented
    -0.75
    wareness
    -0.71
    Pratique
    -0.70
     Audiodateien
    -0.69
    documented
    -0.69
     }}"></
    -0.68
    aderie
    -0.68
     MessageBoxIcon
    -0.67
    POSITIVE LOGITS
     choice
    1.77
     choices
    1.62
     Choice
    1.59
     Choosing
    1.57
     choosing
    1.54
     choose
    1.52
     Choices
    1.52
     chooses
    1.51
     CHOICE
    1.50
     chosen
    1.49
    Act Density 1.500%

    No Known Activations