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

    Neuronpedia

    INDEX
    Explanations

    punctuation and connective phrases reflecting narrative flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whom
    -0.18
    zion
    -0.16
    atron
    -0.15
    ÑĭÑĤ
    -0.14
     Jorge
    -0.14
     suppose
    -0.14
    aha
    -0.14
    azer
    -0.14
    ante
    -0.13
    INK
    -0.13
    POSITIVE LOGITS
     they
    0.29
     there
    0.24
    they
    0.22
     she
    0.19
     has
    0.19
     вони
    0.19
     we
    0.19
     они
    0.17
     There
    0.17
     ìŀĪê³ł
    0.17
    Act Density 0.228%

    No Known Activations