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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate judgment or decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uity
    -0.15
    Äįe
    -0.15
    acket
    -0.14
    inesis
    -0.14
    usu
    -0.14
    owied
    -0.13
    ãģĮãģĦ
    -0.13
    aÄį
    -0.12
    ниÑĨ
    -0.12
    achts
    -0.12
    POSITIVE LOGITS
    ej
    0.14
    ÂĿ
    0.14
    —
    0.14
    NewItem
    0.13
    jer
    0.13
    odd
    0.13
    å¢
    0.13
    (*)(
    0.12
     TMPro
    0.12
    ena
    0.12
    Act Density 0.015%

    No Known Activations