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

    Neuronpedia

    INDEX
    Explanations

    references to theft or stealing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    397
    -0.16
    ForResult
    -0.15
    _requires
    -0.15
    lope
    -0.15
    rophe
    -0.14
    idue
    -0.14
    suming
    -0.14
     Roe
    -0.14
    quisite
    -0.14
    ups
    -0.14
    POSITIVE LOGITS
     away
    0.24
     stealing
    0.20
     thunder
    0.20
     khá»ıi
    0.18
    ambi
    0.18
     ÙħÙĨÙĩا
    0.17
     stole
    0.17
     identities
    0.17
     Away
    0.16
     thief
    0.16
    Act Density 0.049%

    No Known Activations