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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.80
     utafitiHapana
    -0.74
     Theſe
    -0.69
     Efq
    -0.67
    ſelf
    -0.64
     himſelf
    -0.63
     themſelves
    -0.61
     myſelf
    -0.59
    ſelves
    -0.58
     Monfieur
    -0.58
    POSITIVE LOGITS
     so
    0.86
    SequentialGroup
    0.74
     it
    0.73
     we
    0.73
     So
    0.67
    SuspendLayout
    0.67
     therefore
    0.67
     you
    0.66
     he
    0.66
     sure
    0.65
    Act Density 0.085%

    No Known Activations