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-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĤ
    -0.73
    ãĤ¹ãĥĪ
    -0.72
    senal
    -0.70
    tenance
    -0.68
    ãĤŃ
    -0.66
    hammad
    -0.66
     territorial
    -0.66
     bisexual
    -0.65
    ulative
    -0.65
    vasive
    -0.64
    POSITIVE LOGITS
    orks
    1.09
    elfth
    1.06
    ares
    1.04
    ipes
    1.02
    urst
    1.02
    icket
    0.97
    elve
    0.95
    anny
    0.94
    ieth
    0.93
    eenth
    0.93
    Act Density 0.005%

    No Known Activations