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

    Neuronpedia

    INDEX
    Explanations

    words 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
    -0.90
    xual
    -0.75
     Cursed
    -0.75
    gger
    -0.74
    ered
    -0.71
    ñ
    -0.70
    wered
    -0.70
    nant
    -0.67
    inating
    -0.67
    xit
    -0.67
    POSITIVE LOGITS
     relations
    0.75
     norms
    0.73
     democr
    0.71
     amenities
    0.71
     networks
    0.70
     psychologist
    0.69
     engagements
    0.68
     networking
    0.68
    ized
    0.67
     agency
    0.67
    Act Density 0.022%

    No Known Activations