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

    Neuronpedia

    INDEX
    Explanations

    instances of apostrophes and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =$?
    -0.81
    LikeLiked
    -0.80
    tvguidetime
    -0.69
    LikeLike
    -0.68
     ModelExpression
    -0.68
    AppMethodBeat
    -0.66
    -0.65
     Waray
    -0.64
     المتحدة
    -0.64
    ModelState
    -0.63
    POSITIVE LOGITS
     Ender
    0.87
     IOC
    0.70
    ...@
    0.65
     lowa
    0.65
    ‍
    0.63
     Esther
    0.63
     Wordpress
    0.62
     wikipagina
    0.60
     pter
    0.59
    Encyklopedia
    0.59
    Act Density 0.171%

    No Known Activations