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

    Neuronpedia

    INDEX
    Explanations

    words related to social media platform Twitter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the social media platform Twitter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.85
    ãĤŃ
    -0.77
    ++++++++++++++++
    -0.74
    senal
    -0.74
     PRESS
    -0.71
    ãĤ¹ãĥĪ
    -0.71
    HAEL
    -0.68
    ãĥ¥
    -0.65
    TAIN
    -0.64
     appropriation
    -0.64
    POSITIVE LOGITS
    elve
    1.29
    enty
    1.23
    orks
    1.22
    elfth
    1.14
    ixt
    1.07
    inkle
    1.04
    ilight
    1.03
    anny
    1.02
    ipes
    1.02
    itching
    1.00
    Act Density 0.016%

    No Known Activations