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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preference or love for specific things or actions

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the phrase "I love the" followed by various subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Loading
    -0.90
    ģĸ
    -0.79
    SPONSORED
    -0.77
     whence
    -0.77
     wherein
    -0.75
    udder
    -0.71
    uthor
    -0.71
    edia
    -0.71
    imester
    -0.70
    ONY
    -0.70
    POSITIVE LOGITS
     idea
    1.55
     simplicity
    1.18
     concept
    1.15
     notion
    1.11
     vibe
    1.04
     smell
    1.04
     fact
    1.03
     flexibility
    1.02
     way
    1.00
     thrill
    0.98
    Act Density 0.196%

    No Known Activations