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

    Neuronpedia

    INDEX
    Explanations

    unique or special characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.20
    )
    -0.18
    :
    -0.18
    ly
    -0.18
     for
    -0.17
    -St
    -0.17
     or
    -0.17
    -S
    -0.17
    -0.17
    &#
    -0.17
    POSITIVE LOGITS
    0.54
    Âł
    0.24
    ãĢĢ
    0.24
    unities
    0.18
    0.18
    		↵
    0.17
    ipsis
    0.17
    neas
    0.17
    .ejb
    0.17
    aida
    0.16
    Act Density 0.038%

    No Known Activations