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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts related to infidelity and its moral implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĤ
    -0.16
    utes
    -0.16
    utos
    -0.15
     forefront
    -0.15
     dang
    -0.14
    UTO
    -0.14
    Äįet
    -0.14
    actics
    -0.14
     flatt
    -0.14
    tet
    -0.14
    POSITIVE LOGITS
    .showMessage
    0.14
    ç»Ŀ
    0.14
    resse
    0.14
    bildung
    0.14
    çµ
    0.14
    ros
    0.13
     doz
    0.13
    anean
    0.13
    åĽ
    0.13
    oe
    0.13
    Act Density 0.130%

    No Known Activations