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

    Neuronpedia

    INDEX
    Explanations

    references to social class and class distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finity
    -0.15
    insula
    -0.15
    ose
    -0.14
    orra
    -0.14
    affer
    -0.14
    urses
    -0.14
    elm
    -0.13
    Ĥ¤
    -0.13
    arium
    -0.13
    angu
    -0.13
    POSITIVE LOGITS
    akat
    0.18
     crafts
    0.16
    craft
    0.16
     craft
    0.16
    SizeMode
    0.15
    Craft
    0.15
     Futures
    0.15
    ippo
    0.14
    ODE
    0.14
     Craft
    0.14
    Act Density 0.018%

    No Known Activations