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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shit
    -0.16
    sss
    -0.16
    935
    -0.16
    ve
    -0.15
    tring
    -0.15
    971
    -0.15
    ss
    -0.15
     seul
    -0.14
    son
    -0.14
    leans
    -0.14
    POSITIVE LOGITS
    curity
    0.22
    quence
    0.21
    責
    0.17
    è´£
    0.17
    cond
    0.16
     meisten
    0.15
     beiden
    0.15
    ahlen
    0.14
    sut
    0.14
    quential
    0.14
    Act Density 0.119%

    No Known Activations