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

    Neuronpedia

    INDEX
    Explanations

    phrases related to love and interconnectedness

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to love and its complex nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.78
    ħĭ
    -0.76
    UMP
    -0.74
    etheless
    -0.66
    arthed
    -0.64
     Seym
    -0.64
    ENTION
    -0.61
    untled
    -0.61
    Option
    -0.60
     Adjusted
    -0.59
    POSITIVE LOGITS
     belongs
    1.61
     exists
    1.44
     shines
    1.42
     hurts
    1.39
     teaches
    1.37
     governs
    1.37
     lasts
    1.35
     grows
    1.34
     binds
    1.33
     matters
    1.33
    Act Density 0.498%

    No Known Activations