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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical data or coding information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     avoient
    -0.91
     auroit
    -0.85
     zelve
    -0.85
     ainfi
    -0.84
     houſe
    -0.80
     auffi
    -0.80
     myſelf
    -0.80
     Jefus
    -0.78
     purpoſe
    -0.78
     juſ
    -0.77
    POSITIVE LOGITS
     lu
    0.49
     l
    0.48
     cla
    0.47
     ben
    0.47
     gi
    0.47
     le
    0.45
     di
    0.45
     it
    0.45
     fig
    0.45
    sche
    0.45
    Act Density 0.174%

    No Known Activations