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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "love"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "love" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.85
    TPPStreamerBot
    -0.79
    SPONSORED
    -0.78
    icter
    -0.75
    ħĭ
    -0.74
    izarre
    -0.70
     enthusi
    -0.69
    interstitial
    -0.68
     helicop
    -0.67
    ynski
    -0.66
    POSITIVE LOGITS
    birds
    0.97
    making
    0.95
    joy
    0.94
     loving
    0.92
     affair
    0.91
    fully
    0.88
    ably
    0.87
     uncond
    0.84
     love
    0.84
    bird
    0.82
    Act Density 0.027%

    No Known Activations