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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ability
    -0.76
    BIP
    -0.75
    WARD
    -0.72
    lance
    -0.72
    idae
    -0.70
    acea
    -0.67
    MSN
    -0.67
    oS
    -0.66
    someone
    -0.66
    Phys
    -0.66
    POSITIVE LOGITS
     entrances
    1.73
     warehouses
    1.72
     residences
    1.71
     buildings
    1.70
     houses
    1.68
     mosques
    1.67
     shelters
    1.67
     neighborhoods
    1.67
     locations
    1.66
     homes
    1.65
    Act Density 0.516%

    No Known Activations