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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "do" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.98
     ſtate
    -0.92
     perſon
    -0.88
     itſelf
    -0.82
     ſever
    -0.81
     ſche
    -0.79
     ftate
    -0.78
     Efq
    -0.78
     purpoſe
    -0.77
     Houſe
    -0.77
    POSITIVE LOGITS
     done
    1.66
     do
    1.59
     doing
    1.51
    Doing
    1.43
     Doing
    1.39
     DOING
    1.39
    doing
    1.34
     Do
    1.28
     DONE
    1.27
     doin
    1.23
    Act Density 0.210%

    No Known Activations