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

    Neuronpedia

    INDEX
    Explanations

    patterns of characters or text structures in a highly technical or coded format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pora
    -0.83
    ramid
    -0.80
    apon
    -0.78
    acho
    -0.75
    apore
    -0.73
    avorite
    -0.73
    itsch
    -0.73
    ahon
    -0.73
    maxwell
    -0.72
    ierrez
    -0.72
    POSITIVE LOGITS
    åij
    0.75
    éĥ
    0.69
    å®
    0.67
    åĪ
    0.67
    人
    0.66
     Bomber
    0.64
    ç«
    0.63
    åĽ
    0.63
    å¼
    0.62
    å¹
    0.62
    Act Density 0.204%

    No Known Activations