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

    Neuronpedia

    INDEX
    Explanations

    special characters or mathematical symbols in formatted text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     graduated
    -0.92
    Graduated
    -0.79
     graduating
    -0.79
     graduates
    -0.76
     gradu
    -0.75
     graduation
    -0.75
     Gradu
    -0.75
    Gradu
    -0.74
    gradu
    -0.71
    Graduation
    -0.68
    POSITIVE LOGITS
    }_{
    1.09
    }}_{
    0.77
    }_
    0.74
    )}_{
    0.69
    _{
    0.64
    msub
    0.57
     }_{
    0.56
    ]_{
    0.55
    }}_
    0.53
     kasarigan
    0.52
    Act Density 0.247%

    No Known Activations