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

    Neuronpedia

    INDEX
    Explanations

    resources and instructional content related to a variety of topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.48
     Infórmanos
    -0.47
    ołnier
    -0.37
    Хьажоргаш
    -0.36
    ércoles
    -0.36
    Související
    -0.35
     surla
    -0.35
    washingtonpost
    -0.35
    RectangleBorder
    -0.34
    Consejo
    -0.34
    POSITIVE LOGITS
     manual
    1.73
     guide
    1.69
     handbook
    1.57
     Manual
    1.55
     Guide
    1.52
    manual
    1.48
    Manual
    1.41
     Handbook
    1.31
    Guide
    1.31
    guide
    1.31
    Act Density 0.850%

    No Known Activations