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

    Neuronpedia

    INDEX
    Explanations

    instances where the verb "taught" appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    the concept of teaching or education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actions
    -0.68
     excess
    -0.65
     exit
    -0.63
     termination
    -0.62
     sources
    -0.62
     receipts
    -0.62
     details
    -0.60
     caps
    -0.60
     Bulk
    -0.60
     leak
    -0.59
    POSITIVE LOGITS
     taught
    3.78
     teaches
    2.40
     teach
    2.22
     teaching
    1.81
     preached
    1.80
     Teach
    1.72
     Teaching
    1.71
     coached
    1.57
     practiced
    1.51
     commanded
    1.43
    Act Density 0.020%

    No Known Activations