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

    Neuronpedia

    INDEX
    Explanations

    phrases related to family dynamics and living arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹Ļ
    -0.15
     spoiled
    -0.15
    interactive
    -0.15
    .addElement
    -0.14
     Latitude
    -0.14
    ano
    -0.14
    Faces
    -0.14
    icher
    -0.14
    Interactive
    -0.14
    اط
    -0.14
    POSITIVE LOGITS
    loven
    0.16
    unks
    0.16
    dech
    0.15
    vens
    0.15
    unk
    0.14
     ëĭ¬
    0.14
    infeld
    0.14
    ĸ
    0.14
    ccoli
    0.14
    ĩ
    0.13
    Act Density 0.126%

    No Known Activations