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

    Neuronpedia

    INDEX
    Explanations

    references to conflict or conflicts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ecosystem
    -0.85
    RefNanny
    -0.83
     shepherds
    -0.80
     Cili
    -0.79
     Otter
    -0.79
    adaptiveStyles
    -0.77
     Serif
    -0.77
     Shepherds
    -0.77
     otter
    -0.76
     terce
    -0.75
    POSITIVE LOGITS
    conf
    1.45
    Conf
    1.41
     Conf
    1.40
     conf
    1.32
     CONF
    0.96
    CONF
    0.85
     Confeder
    0.73
    idoscope
    0.73
     confeder
    0.69
     Confucius
    0.68
    Act Density 0.009%

    No Known Activations