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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word 'love'

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "love" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.75
    abad
    -0.70
    SpaceEngineers
    -0.63
     Incarnation
    -0.63
    shr
    -0.63
    enance
    -0.62
    umble
    -0.62
    interstitial
    -0.62
    oran
    -0.62
    ionic
    -0.60
    POSITIVE LOGITS
    tsky
    1.13
    rer
    1.10
    rers
    1.07
    lette
    1.01
     Albion
    0.98
    tail
    0.96
    ments
    0.93
    nesday
    0.93
    tails
    0.90
    mented
    0.87
    Act Density 0.020%

    No Known Activations