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

    Neuronpedia

    INDEX
    Explanations

    references to personal ownership or individuality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.20
     Himself
    -0.16
     himself
    -0.16
     herself
    -0.16
     oneself
    -0.15
    strand
    -0.15
     Dump
    -0.14
     Mansion
    -0.14
    776
    -0.14
    conte
    -0.14
    POSITIVE LOGITS
     version
    0.17
    ledge
    0.17
    -brand
    0.16
    ständ
    0.16
    PFN
    0.15
     respective
    0.15
    agher
    0.15
    971
    0.15
    -ÑĤаки
    0.14
    ERGY
    0.14
    Act Density 0.037%

    No Known Activations