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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.77
    emis
    -0.75
    ciples
    -0.75
    IDE
    -0.73
    ¥ŀ
    -0.72
    isively
    -0.71
    IDES
    -0.70
    hire
    -0.70
    £ı
    -0.69
    ģĸ
    -0.69
    POSITIVE LOGITS
    's
    1.29
     sounds
    1.14
     sucks
    1.13
     guy
    1.09
     sounded
    1.08
     ain
    1.06
     reminds
    1.05
    'll
    1.04
     settles
    1.01
     bastard
    1.00
    Act Density 0.122%

    No Known Activations