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

    Neuronpedia

    INDEX
    Explanations

    promotional phrases inviting action or engagement

    oai_token-act-pair · gpt-3.5-turbo

    commands or phrases related to obtaining or enjoying experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RFC
    -0.68
    existent
    -0.59
    pires
    -0.59
     retard
    -0.58
    impl
    -0.58
     mishand
    -0.58
    mith
    -0.57
    rafted
    -0.57
    arthed
    -0.56
    pher
    -0.55
    POSITIVE LOGITS
     Yourself
    0.90
     yourself
    0.87
    tainment
    0.87
     yourselves
    0.85
     yours
    0.83
    INGS
    0.81
     Online
    0.79
     CLICK
    0.79
     browsing
    0.76
    quartered
    0.76
    Act Density 0.257%

    No Known Activations