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

    Neuronpedia

    INDEX
    Explanations

    references to Boston College and related abbreviations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Polonia
    -0.79
     pata
    -0.79
     Dahlia
    -0.78
     Infan
    -0.76
     Yarm
    -0.76
     Tuan
    -0.74
     Ramb
    -0.73
    듭
    -0.73
     Cama
    -0.71
     Nio
    -0.70
    POSITIVE LOGITS
     BC
    1.40
    BC
    1.16
     BCG
    1.05
     bc
    1.03
     Bc
    1.03
    bc
    0.97
    Bc
    0.85
    bouncycastle
    0.79
    xbc
    0.79
     bess
    0.78
    Act Density 0.008%

    No Known Activations