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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awtextra
    -0.95
    gjenge
    -0.90
     contextLoads
    -0.85
    ésult
    -0.84
     iſt
    -0.83
    archiw
    -0.82
    HttpFoundation
    -0.79
     '{@
    -0.78
    ércoles
    -0.78
    ENEFITS
    -0.78
    POSITIVE LOGITS
     }}"
    0.85
    .}
    0.80
    ).}
    0.79
    "}
    0.78
    !}
    0.76
    ）.
    0.76
    }.
    0.74
    $.}
    0.73
    ])).
    0.73
     }}
    0.72
    Act Density 0.213%

    No Known Activations