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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used for sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=
    -0.68
    "]="
    -0.64
    ratulations
    -0.63
    ]+=
    -0.63
    ')]
    -0.61
     CURIAM
    -0.57
    exels
    -0.57
    })=\
    -0.56
    ']=
    -0.55
    )$}
    -0.55
    POSITIVE LOGITS
     which
    1.35
     and
    1.31
    and
    1.20
     but
    1.18
    which
    1.17
     with
    1.16
     as
    1.04
     or
    1.03
     because
    1.00
    but
    0.96
    Act Density 0.377%

    No Known Activations