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

    Neuronpedia

    INDEX
    Explanations

    the word "so" in various contexts of usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.85
    ſelf
    -0.85
     Cæsar
    -0.81
     myſelf
    -0.80
     Efq
    -0.80
     himſelf
    -0.76
     Monfieur
    -0.74
    ſelves
    -0.73
     Plage
    -0.70
     ―――――
    -0.68
    POSITIVE LOGITS
     so
    0.98
     we
    0.86
     therefore
    0.80
     So
    0.79
    DockStyle
    0.77
     therefor
    0.75
     it
    0.71
    ابراین
    0.70
    ậy
    0.70
     nên
    0.69
    Act Density 0.114%

    No Known Activations