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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "so" used to indicate causal relationships or transitions in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.74
    ſelf
    -0.74
     myſelf
    -0.72
     Theſe
    -0.71
     himſelf
    -0.71
     Efq
    -0.70
    ſelves
    -0.66
     Monfieur
    -0.65
    neſs
    -0.65
     Saltar
    -0.62
    POSITIVE LOGITS
     so
    1.04
     So
    1.00
     therefore
    0.88
     we
    0.84
     Therefore
    0.81
    Therefore
    0.80
    ないので
    0.80
    So
    0.79
     поэтому
    0.79
     nên
    0.78
    Act Density 0.203%

    No Known Activations