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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toep
    -0.58
     notoriously
    -0.57
    sige
    -0.54
    Off
    -0.54
     बजाय
    -0.54
     bang
    -0.52
     Biographie
    -0.52
     blz
    -0.52
     demonios
    -0.52
     propi
    -0.52
    POSITIVE LOGITS
    🤍
    0.75
    بوابة
    0.75
    EndGlobalSection
    0.75
    Compassion
    0.72
     ❤️
    0.72
    ьаж
    0.71
     compassionate
    0.71
     tenderly
    0.68
     ♥️
    0.68
    💙
    0.67
    Act Density 0.249%

    No Known Activations