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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government-run entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "run" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.71
     Hots
    -0.70
    irlf
    -0.70
     Ink
    -0.68
    owder
    -0.66
     degrade
    -0.65
    Bone
    -0.65
    une
    -0.65
    shapeshifter
    -0.64
    ¿½
    -0.64
    POSITIVE LOGITS
    ners
    1.06
    escape
    1.05
    swick
    0.86
    nings
    0.85
    tering
    0.77
    ctors
    0.75
    nered
    0.75
    ters
    0.74
    eways
    0.70
    nell
    0.69
    Act Density 0.025%

    No Known Activations