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

    Neuronpedia

    INDEX
    Explanations

    LaTeX aligned environments used for mathematical equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    findpost
    -0.56
    ksesta
    -0.50
    '
    -0.50
    ->
    -0.49
    Collegamenti
    -0.44
    ないので
    -0.44
    ioutil
    -0.43
    див
    -0.43
     nonUne
    -0.43
     deur
    -0.43
    POSITIVE LOGITS
     itſelf
    0.95
     Efq
    0.90
     ―――――
    0.88
     myſelf
    0.87
    Alike
    0.77
     ſeveral
    0.74
     ――――――――
    0.74
    neſs
    0.73
     Theſe
    0.71
    SizeMode
    0.70
    Act Density 0.010%

    No Known Activations