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

    Neuronpedia

    INDEX
    Explanations

    references to previously mentioned information or discussions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
    LookAnd
    -0.67
     ComVisible
    -0.66
    Geplaatst
    -0.61
    UnknownFieldSet
    -0.57
    AntiForgeryToken
    -0.56
    ResumeLayout
    -0.54
    LikeLiked
    -0.53
     дописавши
    -0.53
    leby
    -0.52
    POSITIVE LOGITS
     elsewhere
    1.09
     earlier
    0.80
     previously
    0.76
     extensively
    0.72
     ailleurs
    0.68
     eloquently
    0.68
    previously
    0.65
     briefly
    0.65
     explicitly
    0.64
     nowhere
    0.63
    Act Density 0.700%

    No Known Activations