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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "put."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -1.12
    SPONSORED
    -0.70
    2019
    -0.70
     fixme
    -0.67
    riott
    -0.66
    DAQ
    -0.66
     Nanto
    -0.65
     Logged
    -0.64
    ESS
    -0.64
    CLOSE
    -0.64
    POSITIVE LOGITS
    ongh
    0.94
     forth
    0.90
     aloud
    0.81
    tun
    0.73
     put
    0.72
     pus
    0.72
    tering
    0.71
     toxins
    0.70
    uca
    0.68
     down
    0.68
    Act Density 0.041%

    No Known Activations