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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safe, supportive, and positive environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubar
    -0.16
    elmet
    -0.15
    ÑĹв
    -0.15
    xis
    -0.14
    оваÑĢ
    -0.14
    andon
    -0.14
    ewitness
    -0.13
    ucci
    -0.13
    erp
    -0.13
    /***/
    -0.13
    POSITIVE LOGITS
     warm
    0.29
     safe
    0.29
     atmosphere
    0.27
     welcoming
    0.27
     accepting
    0.26
     atmos
    0.26
     judgement
    0.25
     fun
    0.25
     judgment
    0.24
     friendly
    0.24
    Act Density 0.105%

    No Known Activations