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

    Neuronpedia

    INDEX
    Explanations

    social media handles or usernames

    oai_token-act-pair · gpt-3.5-turbo

    usernames or handles from social media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     charact
    -0.64
     streng
    -0.62
     reorgan
    -0.62
     surging
    -0.62
     unequ
    -0.61
     tha
    -0.61
     relegation
    -0.59
     stigmat
    -0.59
     delic
    -0.58
     heed
    -0.57
    POSITIVE LOGITS
    Jr
    0.99
    mma
    0.89
    TX
    0.88
    MD
    0.87
    NFL
    0.87
    DC
    0.86
    CT
    0.84
    music
    0.84
    007
    0.83
    _
    0.82
    Act Density 0.080%

    No Known Activations