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

    Neuronpedia

    INDEX
    Explanations

    terms related to radical changes or ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regula
    -0.68
    XmlAccessorType
    -0.65
    Joyce
    -0.64
    Бахар
    -0.63
    Dawson
    -0.62
    Nay
    -0.62
    alamus
    -0.62
     exces
    -0.62
    ță
    -0.61
     Taras
    -0.60
    POSITIVE LOGITS
     radical
    0.91
     ju
    0.88
    radical
    0.87
    Radical
    0.85
    Ju
    0.85
     Radical
    0.83
    EnableWeb
    0.83
     Ju
    0.82
     Bourgoin
    0.75
     radikal
    0.69
    Act Density 0.191%

    No Known Activations