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

    Neuronpedia

    INDEX
    Explanations

    mentions of the social media platform Twitter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter and its related functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cision
    -0.70
    cised
    -0.69
     Starr
    -0.67
     Scandinavian
    -0.67
    olphin
    -0.66
     Vie
    -0.66
    minded
    -0.64
    istries
    -0.64
     Dahl
    -0.63
     Samoa
    -0.62
    POSITIVE LOGITS
    storms
    0.90
     hashtag
    0.89
     hasht
    0.88
    @@@@@@@@
    0.82
    storm
    0.79
     feeds
    0.78
     handles
    0.77
    TW
    0.76
     (@
    0.75
     users
    0.74
    Act Density 0.034%

    No Known Activations