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

    Neuronpedia

    INDEX
    Explanations

    elements related to social dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìłij
    -0.19
    sehen
    -0.17
     Leben
    -0.15
     Pentagon
    -0.15
     ç¼
    -0.14
     Unternehmen
    -0.14
    achten
    -0.14
     Blick
    -0.14
     Fragen
    -0.14
    reiben
    -0.14
    POSITIVE LOGITS
    ierung
    0.25
    igkeit
    0.23
    altung
    0.22
    ematik
    0.19
    uppe
    0.19
    stellung
    0.19
    seite
    0.18
    pause
    0.18
    chaft
    0.18
    ität
    0.18
    Act Density 0.040%

    No Known Activations