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

    Neuronpedia

    INDEX
    Explanations

    repeated sequences or patterns related to coding or programming

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.77
    rawDesc
    -0.53
    izr
    -0.52
    fathers
    -0.51
     Pat
    -0.50
    gmd
    -0.49
    বহ
    -0.48
     Mako
    -0.47
     handleMessage
    -0.47
     الحره
    -0.47
    POSITIVE LOGITS
     themſelves
    0.75
     automatiques
    0.74
     reaſon
    0.72
     itſelf
    0.70
     leſs
    0.68
     himſelf
    0.66
    otras
    0.65
     Efq
    0.65
     wikipagina
    0.64
     Chriftian
    0.64
    Act Density 0.003%

    No Known Activations