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

    Neuronpedia

    INDEX
    Explanations

    descriptions of places or environments focusing on social interaction and relaxation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of enjoyable social experiences or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.89
    Matrix
    -0.80
     blacklist
    -0.77
     miscar
    -0.74
     Bastard
    -0.73
     Worse
    -0.72
    abase
    -0.72
    failed
    -0.71
    execute
    -0.71
     draconian
    -0.70
    POSITIVE LOGITS
     enjoyment
    1.42
     relaxation
    1.34
     relaxing
    1.27
     excitement
    1.26
     enjoyable
    1.25
     fun
    1.24
     spont
    1.23
     comr
    1.19
     festive
    1.19
     laughter
    1.16
    Act Density 0.461%

    No Known Activations