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

    Neuronpedia

    INDEX
    Explanations

    the word "throughout."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.83
    n
    -0.80
    -
    -0.79
    o
    -0.73
     or
    -0.71
    1
    -0.71
    2
    -0.71
    /
    -0.70
     sal
    -0.70
     “
    -0.68
    POSITIVE LOGITS
    throughout
    2.84
     throughout
    2.66
     Throughout
    2.29
    Throughout
    2.23
     THRO
    1.64
    HOUT
    1.63
     myſelf
    1.30
     sepanjang
    1.30
     themſelves
    1.29
     partout
    1.29
    Act Density 0.035%

    No Known Activations