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

    Neuronpedia

    INDEX
    Explanations

    references to the use of 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
    -0.95
    ilts
    -0.74
    ARDS
    -0.70
     Salvation
    -0.69
    urat
    -0.67
    forth
    -0.66
     Ridge
    -0.66
    shall
    -0.63
    ress
    -0.63
    atche
    -0.62
    POSITIVE LOGITS
     networking
    1.03
     networks
    1.01
    izing
    0.94
    ize
    0.84
     media
    0.84
    ized
    0.81
     bookmark
    0.80
    IZE
    0.80
     network
    0.80
    ization
    0.78
    Act Density 0.026%

    No Known Activations