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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achieving specific goals or outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    reach
    -0.72
    an
    -0.72
     bross
    -0.69
    Sk
    -0.68
    ness
    -0.67
    last
    -0.66
    Reach
    -0.66
     Reaching
    -0.66
    REACH
    -0.66
     Millard
    -0.66
    POSITIVE LOGITS
    extAlignment
    1.23
    ThemeOverlay
    0.98
    HasAnnotation
    0.88
     للمعارف
    0.86
    batore
    0.85
     myrtle
    0.85
    ukone
    0.84
    0.83
    Criterion
    0.82
     IEA
    0.82
    Act Density 0.013%

    No Known Activations