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

    Neuronpedia

    INDEX
    Explanations

    locations or structures of importance or strength

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with locations and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.80
    lessly
    -0.68
     drunk
    -0.64
    é¾įå¥ij士
    -0.63
     dod
    -0.62
     cured
    -0.62
     sear
    -0.61
     loving
    -0.61
     Sergeant
    -0.61
    Ô
    -0.60
    POSITIVE LOGITS
    ices
    1.19
    uments
    1.17
    ations
    1.15
    estones
    1.14
    ctions
    1.13
    ancies
    1.13
    asures
    1.12
    ements
    1.10
    ences
    1.09
    aments
    1.08
    Act Density 0.289%

    No Known Activations