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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that indicate continuity or connection between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agan
    -0.17
    alon
    -0.15
    emean
    -0.15
    avourites
    -0.15
    arti
    -0.15
    earer
    -0.14
    adv
    -0.14
    oub
    -0.14
    arton
    -0.14
    oeff
    -0.14
    POSITIVE LOGITS
    nier
    0.15
    ROWS
    0.14
    icontrol
    0.14
    <::
    0.14
    æ®
    0.14
     Rig
    0.13
    UCH
    0.13
    unami
    0.13
     ÑģÑĤаÑĤ
    0.13
    ynomial
    0.13
    Act Density 0.149%

    No Known Activations