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

    Neuronpedia

    INDEX
    Explanations

    expressions of subjective opinions or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.55
    delwed
    -0.49
     surla
    -0.48
     bVar
    -0.47
     author
    -0.45
    RenderAtEndOf
    -0.45
     Catawiki
    -0.45
    ISupport
    -0.44
    VersionUID
    -0.44
     Semp
    -0.44
    POSITIVE LOGITS
    awtextra
    0.59
     weirdly
    0.54
    basically
    0.52
    bkz
    0.51
     literally
    0.50
     appunto
    0.49
     basically
    0.49
     prolly
    0.48
     freaking
    0.48
     vraiment
    0.47
    Act Density 0.279%

    No Known Activations