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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     now
    -0.18
     ÅŁimdi
    -0.17
    ãĥªãĥ¼ãĤº
    -0.17
    now
    -0.16
     soon
    -0.16
    ume
    -0.15
    ceptar
    -0.15
    roit
    -0.15
    soon
    -0.15
    ival
    -0.14
    POSITIVE LOGITS
    /if
    0.19
     finished
    0.18
     younger
    0.17
     supposed
    0.17
     otherwise
    0.16
    éģĩ
    0.15
     away
    0.15
     supposedly
    0.14
     young
    0.14
     finally
    0.14
    Act Density 0.129%

    No Known Activations