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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military operations and official designations

    oai_token-act-pair · gpt-3.5-turbo

    references to military or defense organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.90
    lasses
    -0.76
    vous
    -0.68
     unders
    -0.65
    cards
    -0.64
    yi
    -0.64
    eners
    -0.63
    ayn
    -0.62
     ease
    -0.62
    deck
    -0.60
    POSITIVE LOGITS
    BILITY
    1.31
    verages
    1.11
    BILITIES
    1.11
    qua
    1.10
    VE
    1.07
    chieve
    1.00
    ircraft
    0.99
    UTH
    0.97
    cknow
    0.96
    HAHA
    0.96
    Act Density 0.050%

    No Known Activations