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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating value or worthiness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     earned
    -0.75
     Earned
    -0.73
     Shoemaker
    -0.73
    earned
    -0.72
     szolg
    -0.68
    deserved
    -0.67
    recie
    -0.66
     pino
    -0.66
     Marlowe
    -0.66
     καλύτε
    -0.66
    POSITIVE LOGITS
     CreateTagHelper
    1.18
    WebVitals
    1.05
     worth
    0.94
     Worth
    0.92
    worth
    0.86
     lenker
    0.83
     WORTH
    0.81
    Worth
    0.79
    mybatisplus
    0.73
    s
    0.73
    Act Density 0.004%

    No Known Activations