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

    Neuronpedia

    INDEX
    Explanations

    the word "love"

    oai_token-act-pair · gpt-3.5-turbo

    references to love and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPPStreamerBot
    -0.86
    ulhu
    -0.83
    SPONSORED
    -0.78
    DERR
    -0.78
    icter
    -0.76
    chnology
    -0.75
     helicop
    -0.75
    vernment
    -0.73
    OTT
    -0.73
    acco
    -0.71
    POSITIVE LOGITS
    joy
    0.99
    making
    0.98
    birds
    0.98
    fully
    0.87
     uncond
    0.86
    giving
    0.86
    ably
    0.85
     affair
    0.84
    bird
    0.82
    fulness
    0.81
    Act Density 0.030%

    No Known Activations