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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a focus on reasonable, responsible, and properly managed actions or entities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     itſelf
    -0.65
     myſelf
    -0.65
    InjectAttribute
    -0.64
    RegressionTest
    -0.63
     caufe
    -0.63
    enumi
    -0.61
     الحره
    -0.61
    ">//
    -0.60
    TagMode
    -0.60
    paksa
    -0.59
    POSITIVE LOGITS
     BrowserModule
    0.57
     Un
    0.56
     unwanted
    0.49
     الرخصة
    0.49
    Geografía
    0.49
    </
    0.48
    ecutable
    0.48
     UN
    0.47
    Un
    0.47
    feof
    0.47
    Act Density 0.044%

    No Known Activations