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

    Neuronpedia

    INDEX
    Explanations

    words related to traditions or traditional practices

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional practices, customs, or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.74
    latest
    -0.69
    mentation
    -0.66
    robe
    -0.64
    ynchron
    -0.62
    anders
    -0.62
    addon
    -0.61
    Recently
    -0.61
    notice
    -0.60
     unres
    -0.60
    POSITIVE LOGITS
    istic
    1.03
    ists
    1.02
    ist
    1.00
    arily
    0.90
    ized
    0.88
    ised
    0.88
    ism
    0.87
    isms
    0.82
    istries
    0.82
    ties
    0.81
    Act Density 0.045%

    No Known Activations