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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "As" at the beginning of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fcn
    -0.17
     eldre
    -0.16
    hci
    -0.16
    following
    -0.16
    inders
    -0.15
    eed
    -0.15
    ISCO
    -0.15
    ãĥ©ãĥ¼
    -0.15
    edu
    -0.15
     behalf
    -0.15
    POSITIVE LOGITS
     always
    0.25
     luck
    0.23
     with
    0.23
    ynchronous
    0.23
    pects
    0.22
     far
    0.21
     noted
    0.21
    ymmetric
    0.20
    ylum
    0.20
    king
    0.20
    Act Density 0.065%

    No Known Activations