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

    Neuronpedia

    INDEX
    Explanations

    references to the process of eliminating or putting an end to something

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    enumi
    -0.68
    GOTREF
    -0.60
    Diweddarwch
    -0.60
     Egon
    -0.59
    jsonwebtoken
    -0.58
     Willoughby
    -0.58
     ब्रेकडाउन
    -0.58
    באנגלית
    -0.57
    atguigu
    -0.56
    adaptiveStyles
    -0.55
    POSITIVE LOGITS
     eradication
    3.20
     eradicate
    2.63
     eradic
    2.42
     eradicated
    2.36
     erad
    1.48
    erad
    1.28
     Era
    0.91
    Era
    0.80
     exter
    0.79
     annihilation
    0.78
    Act Density 0.000%

    No Known Activations