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

    expressions of love or strong affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.91
    thren
    -0.82
    vernment
    -0.75
    acent
    -0.75
    enei
    -0.73
    iban
    -0.73
    interstitial
    -0.73
     reluct
    -0.71
    chnology
    -0.69
    Solution
    -0.67
    POSITIVE LOGITS
    birds
    0.98
     dearly
    0.96
     uncond
    0.89
    joy
    0.84
     watching
    0.79
    fully
    0.76
     seeing
    0.75
    ably
    0.73
     passionately
    0.71
     listening
    0.69
    Act Density 0.045%

    No Known Activations