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

    Neuronpedia

    INDEX
    Explanations

    references to educational achievement and grading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     soft
    -0.41
    TagMode
    -0.40
    MethodManager
    -0.39
     ModelRenderer
    -0.37
     cref
    -0.37
    soft
    -0.37
    々木
    -0.35
    出版年
    -0.34
    insegna
    -0.34
     Soft
    -0.33
    POSITIVE LOGITS
     grad
    1.95
    grad
    1.86
     gradient
    1.83
     graduate
    1.77
     GRAD
    1.76
    Grad
    1.75
     Grad
    1.73
     Gradient
    1.67
    GRAD
    1.62
    graduate
    1.59
    Act Density 0.103%

    No Known Activations