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

    Neuronpedia

    INDEX
    Explanations

    phrases related to carrying out actions or operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to military operations or actions being carried out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.73
    rified
    -0.68
    oxin
    -0.66
    unity
    -0.62
    timer
    -0.62
    Todd
    -0.62
    tal
    -0.62
    username
    -0.61
    uncle
    -0.61
    ener
    -0.60
    POSITIVE LOGITS
     experiments
    1.09
     searches
    1.03
     raids
    1.02
     inspections
    0.97
     abortions
    0.94
     repairs
    0.94
     drills
    0.94
     investigations
    0.94
     reconnaissance
    0.93
     tasks
    0.92
    Act Density 0.105%

    No Known Activations