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

    Neuronpedia

    INDEX
    Explanations

    references to washing or cleaning activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ziej
    -0.17
    opian
    -0.17
    ju
    -0.17
    ecies
    -0.17
    _python
    -0.15
    e
    -0.15
    235
    -0.14
    lei
    -0.14
     AXIS
    -0.14
    reeting
    -0.14
    POSITIVE LOGITS
    (es
    0.22
    room
    0.21
    ingt
    0.20
    rooms
    0.20
    inton
    0.19
    ermen
    0.19
    es
    0.19
    ateria
    0.19
    out
    0.18
     Redskins
    0.18
    Act Density 0.016%

    No Known Activations