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

    Neuronpedia

    INDEX
    Explanations

    possessive forms and contractions of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸ĢäºĽ
    -0.18
    /or
    -0.17
    æĥħåĨµ
    -0.17
    ously
    -0.16
    å£°éŁ³
    -0.16
    ’s
    -0.15
    adel
    -0.15
    ym
    -0.15
    antly
    -0.14
    ombat
    -0.14
    POSITIVE LOGITS
     been
    0.24
     gonna
    0.19
     got
    0.19
    been
    0.19
     Been
    0.18
    nbsp
    0.17
    /fw
    0.17
     gotta
    0.17
    amp
    0.15
    isos
    0.15
    Act Density 0.340%

    No Known Activations