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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and variations of the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iler
    -0.17
    ooks
    -0.16
    pri
    -0.15
    eln
    -0.14
    urt
    -0.14
     件
    -0.14
    ugin
    -0.14
    mers
    -0.14
    ahan
    -0.14
    UGIN
    -0.14
    POSITIVE LOGITS
    imity
    0.15
    arty
    0.14
    176
    0.14
    orts
    0.14
    rary
    0.14
    rez
    0.14
    azi
    0.14
    lector
    0.13
    wich
    0.13
     Linear
    0.13
    Act Density 0.139%

    No Known Activations