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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance and legislative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    192
    -0.21
    194
    -0.17
    swer
    -0.17
    193
    -0.17
    .ManyToMany
    -0.16
     WWII
    -0.16
    196
    -0.15
    195
    -0.15
    amped
    -0.15
    mlin
    -0.15
    POSITIVE LOGITS
     Female
    0.31
    Female
    0.26
     subscription
    0.24
     Mechanics
    0.23
     academy
    0.22
     Literary
    0.21
     Subscription
    0.21
    EMALE
    0.21
     Normal
    0.21
     Male
    0.21
    Act Density 0.043%

    No Known Activations