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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "and" to identify connections or groupings among subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çıį
    -0.14
    olem
    -0.14
    å¬
    -0.14
    crest
    -0.13
    zug
    -0.13
    ÎŃÏģα
    -0.13
    ágenes
    -0.13
    amura
    -0.13
     ëĵ
    -0.13
    anchise
    -0.13
    POSITIVE LOGITS
    omite
    0.16
    329
    0.14
    322
    0.14
    its
    0.14
    opi
    0.13
    hei
    0.13
    ICI
    0.13
     its
    0.13
     пеÑĢен
    0.13
     Tet
    0.12
    Act Density 0.098%

    No Known Activations