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

    Neuronpedia

    INDEX
    Explanations

    notations of uncertainty or potential issues in decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.76
    expandindo
    -0.68
    CodeAttribute
    -0.66
    BufferException
    -0.59
     doInBackground
    -0.54
    colgroup
    -0.54
    -0.53
     كومونز
    -0.51
    sidemargin
    -0.50
    ória
    -0.50
    POSITIVE LOGITS
     translate
    0.62
     translated
    0.60
     translates
    0.60
     quickly
    0.59
     translating
    0.58
    translates
    0.55
     wears
    0.53
    quickly
    0.53
     eat
    0.52
     schnell
    0.51
    Act Density 0.341%

    No Known Activations