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

    Neuronpedia

    INDEX
    Explanations

    content related to social media

    oai_token-act-pair · gpt-3.5-turbo

    references to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -1.01
    urat
    -0.78
    atche
    -0.76
    _-
    -0.68
    sterdam
    -0.66
     Blazing
    -0.65
     Zup
    -0.64
    1001
    -0.64
    ARDS
    -0.64
    shall
    -0.63
    POSITIVE LOGITS
     networks
    1.15
     networking
    1.13
     media
    1.13
    izing
    0.96
    media
    0.90
    ize
    0.90
     network
    0.88
     platforms
    0.87
    ized
    0.87
    izers
    0.86
    Act Density 0.022%

    No Known Activations