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

    Neuronpedia

    INDEX
    Explanations

    the word "poke" or variations of it, such as "poked" or "poking."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to playful teasing or making fun of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sovereign
    -0.80
     Rhod
    -0.79
     Montgomery
    -0.78
     Strat
    -0.75
    reshold
    -0.71
     Saturn
    -0.71
     Lords
    -0.70
    uchs
    -0.69
    cale
    -0.69
     Schwarz
    -0.69
    POSITIVE LOGITS
     poke
    2.60
     poked
    2.26
     poking
    2.24
     jab
    1.82
     Poke
    1.53
     peek
    1.47
     prick
    1.43
    PK
    1.26
     smack
    1.20
     puck
    1.17
    Act Density 0.035%

    No Known Activations