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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing strong positive emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of affection or love towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
    thren
    -0.74
    interstitial
    -0.74
     reluct
    -0.74
    enei
    -0.73
    uum
    -0.72
    otomy
    -0.71
    phrine
    -0.71
     helicop
    -0.71
    iban
    -0.70
    POSITIVE LOGITS
    birds
    0.96
     uncond
    0.94
     dearly
    0.91
    joy
    0.90
    fully
    0.84
     passionately
    0.81
    ably
    0.77
     watching
    0.68
    bird
    0.67
     seeing
    0.67
    Act Density 0.035%

    No Known Activations