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

    Neuronpedia

    INDEX
    Explanations

    negative symbols or signs related to reductions or subtractions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.96
     nahilalakip
    -0.94
    ]")]
    -0.91
    ))]
    -0.87
    ”]
    -0.86
    )]=
    -0.85
    ]?
    -0.84
    )))),
    -0.79
    "])
    -0.79
    ")]
    -0.79
    POSITIVE LOGITS
    ेश
    0.53
    Mount
    0.50
     schia
    0.49
     Mount
    0.48
    Alb
    0.46
     chó
    0.45
    gino
    0.45
    monium
    0.43
     себе
    0.43
     espes
    0.42
    Act Density 0.012%

    No Known Activations