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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owied
    -0.17
    ofi
    -0.17
    fty
    -0.16
    igg
    -0.15
    æŁı
    -0.15
    оÑĨи
    -0.15
    erne
    -0.14
    halten
    -0.14
    orra
    -0.14
    eyed
    -0.14
    POSITIVE LOGITS
     own
    0.20
    el
    0.15
    sing
    0.15
     birthday
    0.15
    holm
    0.14
     travels
    0.14
    227
    0.14
    own
    0.14
     Birthday
    0.14
    547
    0.14
    Act Density 0.262%

    No Known Activations