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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ance
    -0.16
    upp
    -0.15
    ise
    -0.15
    oring
    -0.15
    emet
    -0.14
     Kerr
    -0.14
    hee
    -0.14
    uis
    -0.14
    ander
    -0.14
    onen
    -0.14
    POSITIVE LOGITS
     tens
    0.17
    ifax
    0.17
    izophren
    0.17
     into
    0.16
     kå
    0.16
    ÃĹ↵↵
    0.15
     skeptic
    0.15
    itzer
    0.15
    .googleapis
    0.15
    041
    0.15
    Act Density 0.241%

    No Known Activations