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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions, particularly those involving code

    oai_token-act-pair · gpt-3.5-turbo

    commands involving the term "set."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     finger
    -0.60
     fault
    -0.58
     fruit
    -0.58
     colleges
    -0.57
     misses
    -0.57
     handic
    -0.57
     knees
    -0.57
     prisons
    -0.57
     kidding
    -0.57
     doctors
    -0.56
    POSITIVE LOGITS
    set
    4.14
    sets
    2.83
    SET
    2.10
    Set
    2.06
    setting
    2.03
     set
    1.81
     Set
    1.79
     sets
    1.50
     Sets
    1.30
     SET
    1.27
    Act Density 0.008%

    No Known Activations