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

    Neuronpedia

    INDEX
    Explanations

    URLs from the Twitter platform

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter and related URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IOR
    -0.69
     dile
    -0.63
     situations
    -0.63
     pad
    -0.61
     configuration
    -0.59
     colonies
    -0.59
     Shack
    -0.58
     Gray
    -0.58
     doctrine
    -0.57
     relaxation
    -0.57
    POSITIVE LOGITS
    twitter
    4.37
    Twitter
    2.17
    facebook
    2.02
     twitter
    1.78
    github
    1.51
     Twitter
    1.47
    twitch
    1.43
    youtube
    1.42
    tumblr
    1.41
    wordpress
    1.40
    Act Density 0.019%

    No Known Activations