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

    Neuronpedia

    INDEX
    Explanations

    the word "As" at the beginning of sentences or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    that
    -0.19
    oader
    -0.16
    ãĤĪãģĨ
    -0.16
    oyer
    -0.15
    efon
    -0.15
    theory
    -0.15
    icerca
    -0.15
    overy
    -0.15
    ously
    -0.15
    ouchers
    -0.15
    POSITIVE LOGITS
    p
    0.32
    phalt
    0.30
    he
    0.28
    pen
    0.27
    m
    0.27
    pire
    0.25
    st
    0.25
    i
    0.25
    king
    0.24
    semble
    0.24
    Act Density 0.062%

    No Known Activations