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

    Neuronpedia

    INDEX
    Explanations

    references to legal or judicial matters

    oai_token-act-pair · gpt-3.5-turbo

    discussions centered around the concept of "the" as a focal point in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strate
    -0.75
    andise
    -0.72
    Thumbnail
    -0.71
    eming
    -0.69
    Lu
    -0.68
    tumblr
    -0.66
    iffe
    -0.66
    ftime
    -0.65
    α
    -0.65
    sted
    -0.65
    POSITIVE LOGITS
     same
    1.09
     slightest
    1.06
     easiest
    1.03
     entire
    1.03
     whole
    1.00
     biggest
    0.97
     unthinkable
    0.97
     safest
    0.96
     latter
    0.95
     hardest
    0.94
    Act Density 0.344%

    No Known Activations