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

    Neuronpedia

    INDEX
    Explanations

    commands to be executed in a terminal

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of technical commands typically used in programming or command-line contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.80
    ONSORED
    -0.75
    mbuds
    -0.72
    Rated
    -0.71
    sung
    -0.70
    anton
    -0.69
     Investor
    -0.68
     Beir
    -0.67
     Preferred
    -0.67
    YL
    -0.67
    POSITIVE LOGITS
     commands
    1.05
    eering
    0.95
     command
    0.92
    stration
    0.92
     cmd
    0.86
    command
    0.84
     sender
    0.83
     prompt
    0.81
     injection
    0.78
     parser
    0.77
    Act Density 0.010%

    No Known Activations