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

    Neuronpedia

    INDEX
    Explanations

    references to hoods or hooded garments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quis
    -0.17
    geber
    -0.15
    UTOR
    -0.15
    apper
    -0.15
    tran
    -0.15
    ube
    -0.15
     Wilde
    -0.14
    nels
    -0.14
    cce
    -0.14
    axon
    -0.14
    POSITIVE LOGITS
    lum
    0.34
    oo
    0.23
    ed
    0.22
     Hood
    0.22
    rat
    0.21
    ies
    0.20
    rats
    0.19
    ie
    0.17
     Nack
    0.17
     hood
    0.16
    Act Density 0.005%

    No Known Activations