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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and resolutions

    oai_token-act-pair · gpt-3.5-turbo

    intent to take action or deliver commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.85
     strikingly
    -0.74
    quartered
    -0.71
     controvers
    -0.64
     famously
    -0.64
     notoriously
    -0.63
     allegedly
    -0.61
     recently
    -0.59
    ected
    -0.58
     dubbed
    -0.57
    POSITIVE LOGITS
     tomorrow
    1.12
     âĢ¦"
    0.96
     ..."
    0.96
     someday
    0.95
    !"
    0.94
     fuckin
    0.87
     yourselves
    0.87
     myself
    0.86
    morrow
    0.85
    !'"
    0.85
    Act Density 1.079%

    No Known Activations