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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    was appointed or elected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    absolutely
    -0.36
     était
    -0.33
    Altri
    -0.33
     absolutely
    -0.33
     Näch
    -0.33
     être
    -0.32
     perfectamente
    -0.32
     vasta
    -0.32
     estar
    -0.32
    very
    -0.32
    POSITIVE LOGITS
     chofe
    0.65
     queſta
    0.61
     become
    0.59
     appointed
    0.58
     renamed
    0.57
     dijadikan
    0.57
     elected
    0.56
     became
    0.56
    featureID
    0.56
     Photocase
    0.56
    Act Density 0.060%

    No Known Activations