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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    instances of imperative verbs and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    printf
    -0.76
    potion
    -0.69
     [*
    -0.65
    ranch
    -0.64
    Created
    -0.61
    omer
    -0.61
    cross
    -0.61
    andowski
    -0.60
    pit
    -0.60
    static
    -0.60
    POSITIVE LOGITS
     yourselves
    1.18
     Yourself
    1.11
     yourself
    1.07
     wisely
    0.70
     CARE
    0.69
     Skies
    0.68
    !:
    0.66
     Geek
    0.66
     Intake
    0.65
     your
    0.64
    Act Density 0.354%

    No Known Activations