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

    Neuronpedia

    INDEX
    Explanations

    pronouns and words indicating personal connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.17
    atron
    -0.17
     Garner
    -0.15
    ullen
    -0.15
    disconnect
    -0.14
    osed
    -0.14
    aul
    -0.14
    .cp
    -0.14
     å¸Ĥ
    -0.14
    AWN
    -0.14
    POSITIVE LOGITS
    inke
    0.15
    Ïĥκε
    0.14
     ke
    0.14
     skeletal
    0.14
     so
    0.14
    gambar
    0.14
    øre
    0.14
    ype
    0.14
    iseum
    0.14
    atta
    0.13
    Act Density 0.000%

    No Known Activations