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

    Neuronpedia

    INDEX
    Explanations

    questions and assertions related to properties or characteristics of objects or concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.77
    amaño
    -0.77
     Theſe
    -0.77
     nephe
    -0.75
     whoſe
    -0.75
     Shakspeare
    -0.73
     makeStyles
    -0.73
     kasarigan
    -0.73
    parsedMessage
    -0.73
    eseorang
    -0.71
    POSITIVE LOGITS
      
    0.60
     r
    0.54
     Ber
    0.51
    M
    0.50
    D
    0.50
     ri
    0.50
     from
    0.49
    esty
    0.49
     solution
    0.49
    roids
    0.48
    Act Density 0.017%

    No Known Activations