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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles to follow or contact

    oai_token-act-pair · gpt-3.5-turbo

    references to social media handles and following instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forgiven
    -0.78
    raints
    -0.65
    forced
    -0.64
    etheless
    -0.63
    raped
    -0.62
    venge
    -0.57
    bably
    -0.56
     hindsight
    -0.55
    ģĸ
    -0.54
    nai
    -0.54
    POSITIVE LOGITS
     @
    1.04
     twitter
    0.99
     (@
    0.95
     Twitter
    0.85
     facebook
    0.85
     tweets
    0.84
    twitter
    0.83
    Website
    0.79
    edin
    0.79
     Tweet
    0.79
    Act Density 0.035%

    No Known Activations