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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and related punctuation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SPATH
    -0.83
    SBATCH
    -0.81
    Esther
    -0.79
     Esther
    -0.75
    ЧИТА
    -0.73
    OSSARY
    -0.72
    ciclop
    -0.72
    arding
    -0.68
     Polly
    -0.68
    ldo
    -0.68
    POSITIVE LOGITS
    »
    1.26
    »»
    1.22
    ,»
    1.21
    ?»
    1.20
    !»
    1.17
    …»
    1.16
    )»
    1.13
    ...»
    1.11
    .»
    1.06
    ».
    1.00
    Act Density 0.001%

    No Known Activations