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

    Neuronpedia

    INDEX
    Explanations

    social media links, specifically from the platform Twitter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter URLs or references to Twitter in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.69
    senal
    -0.67
     Sinclair
    -0.65
    erella
    -0.65
    ailability
    -0.62
     consultation
    -0.62
     ageing
    -0.62
     fertility
    -0.62
     defense
    -0.61
     deliber
    -0.61
    POSITIVE LOGITS
    twitter
    1.14
    #$
    0.90
    cdn
    0.86
    ðŁ
    0.83
     Appears
    0.82
    youtu
    0.81
    externalActionCode
    0.78
     (@
    0.77
    à
    0.77
     "@
    0.76
    Act Density 0.012%

    No Known Activations