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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    juan
    -0.15
    311
    -0.15
    arsi
    -0.14
     Cres
    -0.14
    еÑģп
    -0.14
    aris
    -0.14
    924
    -0.14
    rof
    -0.13
    ulton
    -0.13
    331
    -0.13
    POSITIVE LOGITS
    /us
    0.17
    Ñĥда
    0.16
    zelf
    0.14
    åĢij
    0.14
     into
    0.14
    اÙĦÛĮ
    0.14
    ÙĬاÙĨ
    0.13
    instein
    0.13
    liches
    0.13
    ALI
    0.13
    Act Density 0.183%

    No Known Activations