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

    Neuronpedia

    INDEX
    Explanations

    the word "throughout" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    n
    -0.98
    al
    -0.85
    o
    -0.84
    a
    -0.84
    6
    -0.77
    1
    -0.76
    2
    -0.76
     “
    -0.76
     sal
    -0.75
    4
    -0.74
    POSITIVE LOGITS
    throughout
    1.38
    HOUT
    1.30
     myſelf
    1.23
     itſelf
    1.23
    MLLoader
    1.21
     themſelves
    1.16
    InputBorder
    1.15
     تضيفلها
    1.13
     throughout
    1.12
     Tutte
    1.11
    Act Density 0.044%

    No Known Activations