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

    Neuronpedia

    INDEX
    Explanations

    themes related to romantic relationships and infidelity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding or related to love and relationships

    np_acts-logits-general · gemini-2.0-flash

    romantic relationships and affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.90
     ſche
    -0.84
     Efq
    -0.84
     purpoſe
    -0.83
     juſ
    -0.83
     reaſon
    -0.81
     myſelf
    -0.79
     ―――――
    -0.78
     himſelf
    -0.78
    ſelf
    -0.77
    POSITIVE LOGITS
     married
    0.56
    Personendaten
    0.56
    KommentareTeilen
    0.51
    對象
    0.48
     ơn
    0.47
     rejected
    0.46
    Ligações
    0.45
    __':
    0.44
    rejected
    0.44
    Chham
    0.43
    Act Density 0.151%

    No Known Activations