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

    Neuronpedia

    INDEX
    Explanations

    references to attitudes or beliefs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.91
    __*/
    -0.89
    </i>
    -0.84
    DataAnnotations
    -0.80
    InputBorder
    -0.75
    /*
    -0.73
    Ours
    -0.72
     onCancelled
    -0.72
    <i>
    -0.71
    queles
    -0.71
    POSITIVE LOGITS
     attitudes
    1.60
     Attitude
    1.58
     attitude
    1.57
     Attitudes
    1.54
    Attitude
    1.50
    attitude
    1.45
    titudes
    1.16
     actitud
    1.11
     actitudes
    1.05
    TITUDE
    0.97
    Act Density 0.002%

    No Known Activations