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

    Neuronpedia

    INDEX
    Explanations

    attributes and descriptors related to architectural structures and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eman
    -0.17
    emale
    -0.17
    arkin
    -0.16
    emer
    -0.16
    pz
    -0.14
    éry
    -0.14
    ark
    -0.14
    ery
    -0.14
    alse
    -0.14
    ancel
    -0.14
    POSITIVE LOGITS
    illage
    0.17
    iffer
    0.16
    iller
    0.15
     retire
    0.15
    ix
    0.14
     Cousins
    0.14
     Couch
    0.14
     AIM
    0.14
     faction
    0.14
    nia
    0.14
    Act Density 0.070%

    No Known Activations