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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Montal
    -0.72
    inq
    -0.69
     Nis
    -0.68
    ('../../../
    -0.68
    vastava
    -0.68
    -¡
    -0.68
    ly
    -0.67
    ècie
    -0.66
     giao
    -0.66
     TimeUnit
    -0.66
    POSITIVE LOGITS
    }}"
    1.15
    )"
    1.08
    %"
    1.08
    ]"
    1.07
    }"
    1.06
    ?"
    1.03
    ')"
    1.03
    "}"
    1.02
     ")"
    1.02
    ')}}"
    1.01
    Act Density 0.131%

    No Known Activations