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

    Neuronpedia

    INDEX
    Explanations

    mentions of naval warships, particularly cruisers

    oai_token-act-pair · gpt-3.5-turbo

    references to cruise ships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spur
    -0.87
     Cause
    -0.72
    quire
    -0.67
    brand
    -0.65
    animate
    -0.64
     Celeb
    -0.61
     guiActiveUnfocused
    -0.61
     Any
    -0.61
    idding
    -0.60
    hend
    -0.59
    POSITIVE LOGITS
     cru
    2.90
     importantly
    1.56
     notably
    1.18
     interestingly
    1.10
     controvers
    1.01
     vo
    0.89
     moreover
    0.88
     impro
    0.86
    etheless
    0.84
     resid
    0.83
    Act Density 0.014%

    No Known Activations