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

    Neuronpedia

    INDEX
    Explanations

    references to individuals with the title "Captain" or "Capt" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to 'Capt' followed by a name or title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tend
    -0.79
    FORE
    -0.72
    senal
    -0.72
    METHOD
    -0.72
    WARE
    -0.70
     prone
    -0.68
     philanthrop
    -0.65
     unlikely
    -0.65
     Nadu
    -0.64
     paternity
    -0.63
    POSITIVE LOGITS
    ains
    1.17
    ained
    1.08
    ivity
    1.06
    Capt
    1.05
    aining
    1.03
    agons
    1.02
    oufl
    1.01
    cha
    1.00
    iles
    0.97
    ilage
    0.94
    Act Density 0.013%

    No Known Activations